From ff5173895cb09f44c48ae20a690b5ee7c1a79968 Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Fri, 8 Nov 2013 10:21:35 -0500 Subject: [PATCH 1/9] minor ui fixes for mac. --- .../sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.form | 4 ++-- .../sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.java | 6 +++--- .../src/org/sleuthkit/autopsy/corecomponents/Installer.java | 6 +----- 3 files changed, 6 insertions(+), 10 deletions(-) diff --git a/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.form b/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.form index ab1236901b..2a2c068ccf 100644 --- a/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.form +++ b/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.form @@ -30,7 +30,7 @@ - + @@ -51,7 +51,7 @@ - + diff --git a/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.java b/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.java index fd399a59ce..3c4dd72bcf 100644 --- a/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.java +++ b/Core/src/org/sleuthkit/autopsy/casemodule/NewCaseVisualPanel1.java @@ -93,7 +93,7 @@ final class NewCaseVisualPanel1 extends JPanel implements DocumentListener{ jLabel2 = new javax.swing.JLabel(); caseDirTextField = new javax.swing.JTextField(); - jLabel1.setFont(new java.awt.Font("Tahoma", 1, 14)); + jLabel1.setFont(new java.awt.Font("Tahoma", 1, 14)); // NOI18N org.openide.awt.Mnemonics.setLocalizedText(jLabel1, org.openide.util.NbBundle.getMessage(NewCaseVisualPanel1.class, "NewCaseVisualPanel1.jLabel1.text_1")); // NOI18N org.openide.awt.Mnemonics.setLocalizedText(caseNameLabel, org.openide.util.NbBundle.getMessage(NewCaseVisualPanel1.class, "NewCaseVisualPanel1.caseNameLabel.text_1")); // NOI18N @@ -133,7 +133,7 @@ final class NewCaseVisualPanel1 extends JPanel implements DocumentListener{ .addComponent(caseParentDirTextField, javax.swing.GroupLayout.PREFERRED_SIZE, 296, javax.swing.GroupLayout.PREFERRED_SIZE)) .addGroup(javax.swing.GroupLayout.Alignment.LEADING, layout.createSequentialGroup() .addComponent(caseNameLabel) - .addGap(26, 26, 26) + .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED, javax.swing.GroupLayout.DEFAULT_SIZE, Short.MAX_VALUE) .addComponent(caseNameTextField, javax.swing.GroupLayout.PREFERRED_SIZE, 296, javax.swing.GroupLayout.PREFERRED_SIZE)) .addComponent(caseDirTextField, javax.swing.GroupLayout.Alignment.LEADING, javax.swing.GroupLayout.PREFERRED_SIZE, 380, javax.swing.GroupLayout.PREFERRED_SIZE)) .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.UNRELATED) @@ -148,7 +148,7 @@ final class NewCaseVisualPanel1 extends JPanel implements DocumentListener{ .addGap(18, 18, 18) .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.BASELINE) .addComponent(caseNameLabel) - .addComponent(caseNameTextField, javax.swing.GroupLayout.PREFERRED_SIZE, 20, javax.swing.GroupLayout.PREFERRED_SIZE)) + .addComponent(caseNameTextField, javax.swing.GroupLayout.PREFERRED_SIZE, javax.swing.GroupLayout.DEFAULT_SIZE, javax.swing.GroupLayout.PREFERRED_SIZE)) .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.UNRELATED) .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.BASELINE) .addComponent(caseDirLabel) diff --git a/Core/src/org/sleuthkit/autopsy/corecomponents/Installer.java b/Core/src/org/sleuthkit/autopsy/corecomponents/Installer.java index ecf5b847b7..61b2bd2cb1 100644 --- a/Core/src/org/sleuthkit/autopsy/corecomponents/Installer.java +++ b/Core/src/org/sleuthkit/autopsy/corecomponents/Installer.java @@ -105,11 +105,7 @@ public class Installer extends ModuleInstall { } final String[] UI_MENU_ITEM_KEYS = new String[]{"MenuBarUI", - "MenuUI", - "MenuItemUI", - "CheckBoxMenuItemUI", - "RadioButtonMenuItemUI", - "PopupMenuUI"}; + }; Map uiEntries = new TreeMap(); From 4ec9d61977bfe23b74fa3dc3ef615ed96e1317f5 Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Fri, 8 Nov 2013 16:44:35 -0500 Subject: [PATCH 2/9] Added DataSource column to BlackboardArtifactNodes. --- .../autopsy/datamodel/BlackboardArtifactNode.java | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java index 5879d6f341..646cb5bcb0 100644 --- a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java +++ b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java @@ -99,6 +99,18 @@ public class BlackboardArtifactNode extends DisplayableItemNode { "Source File", NO_DESCR, associated.getName())); + + String sourceName = ""; + try { + sourceName = associated.getImage().getName(); + } catch (TskCoreException ex) { + logger.log(Level.WARNING, "Failed to get image."); + } + + if (sourceName.isEmpty() == false) { + ss.put(new NodeProperty("Data Source", "Data Source", + NO_DESCR, sourceName)); + } for (Map.Entry entry : map.entrySet()) { ss.put(new NodeProperty(entry.getKey(), From 34007d297907ef0858b899b2e52d9e97c1eea954 Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Mon, 11 Nov 2013 09:44:45 -0500 Subject: [PATCH 3/9] Removed duplicate path columns for some blackboard artifact nodes. --- .../datamodel/BlackboardArtifactNode.java | 31 ++++--------------- .../org/sleuthkit/autopsy/datamodel/Tags.java | 14 --------- 2 files changed, 6 insertions(+), 39 deletions(-) diff --git a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java index 646cb5bcb0..168494b1a9 100644 --- a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java +++ b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java @@ -100,16 +100,16 @@ public class BlackboardArtifactNode extends DisplayableItemNode { NO_DESCR, associated.getName())); - String sourceName = ""; + String sourcePath = ""; try { - sourceName = associated.getImage().getName(); + sourcePath = associated.getUniquePath(); } catch (TskCoreException ex) { - logger.log(Level.WARNING, "Failed to get image."); + logger.log(Level.WARNING, "Failed to get unique path from: " + associated.getName()); } - if (sourceName.isEmpty() == false) { - ss.put(new NodeProperty("Data Source", "Data Source", - NO_DESCR, sourceName)); + if (sourcePath.isEmpty() == false) { + ss.put(new NodeProperty("File Path", "File Path", + NO_DESCR, sourcePath)); } for (Map.Entry entry : map.entrySet()) { @@ -119,30 +119,11 @@ public class BlackboardArtifactNode extends DisplayableItemNode { entry.getValue())); } - String path = ""; - try { - path = associated.getUniquePath(); - } catch (TskCoreException ex) { - logger.log(Level.SEVERE, "Except while calling Content.getUniquePath() on " + associated); - } - final int artifactTypeID = artifact.getArtifactTypeID(); - - //custom additional properties - //TODO use addNodeProperty() instead of hardcoding here - if (artifactTypeID == BlackboardArtifact.ARTIFACT_TYPE.TSK_HASHSET_HIT.getTypeID() - || artifactTypeID == BlackboardArtifact.ARTIFACT_TYPE.TSK_KEYWORD_HIT.getTypeID()) { - ss.put(new NodeProperty("File Path", - "File Path", - NO_DESCR, - path)); - } - //append custom node properties if (customProperties != null) { for (NodeProperty np : customProperties) { ss.put(np); } - } return s; diff --git a/Core/src/org/sleuthkit/autopsy/datamodel/Tags.java b/Core/src/org/sleuthkit/autopsy/datamodel/Tags.java index 11ad9d6498..129091ed21 100644 --- a/Core/src/org/sleuthkit/autopsy/datamodel/Tags.java +++ b/Core/src/org/sleuthkit/autopsy/datamodel/Tags.java @@ -417,20 +417,6 @@ public class Tags implements AutopsyVisitableItem { tagNode.addNodeProperty(resultTypeProp); } - try { - //add source path property - final AbstractFile sourceFile = skCase.getAbstractFileById(artifact.getObjectID()); - final String sourcePath = sourceFile.getUniquePath(); - NodeProperty sourcePathProp = new NodeProperty("Source File Path", - "Source File Path", - NO_DESCR, - sourcePath); - - - tagNode.addNodeProperty(sourcePathProp); - } catch (TskCoreException ex) { - logger.log(Level.SEVERE, "Error getting a file from artifact to get source file path for a tag, ", ex); - } return tagNode; } From 4e9e354a45b4094a5e444cc9f97b1f2a261a2a2f Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Mon, 11 Nov 2013 09:52:40 -0500 Subject: [PATCH 4/9] Line endings. --- thunderbirdparser/nbproject/project.properties | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/thunderbirdparser/nbproject/project.properties b/thunderbirdparser/nbproject/project.properties index 6a243df466..0735c621fa 100644 --- a/thunderbirdparser/nbproject/project.properties +++ b/thunderbirdparser/nbproject/project.properties @@ -1,6 +1,6 @@ -javac.source=1.7 -javac.compilerargs=-Xlint -Xlint:-serial -license.file=../LICENSE-2.0.txt -nbm.homepage=http://www.sleuthkit.org/autopsy/ -nbm.needs.restart=true -spec.version.base=1.2 +javac.source=1.7 +javac.compilerargs=-Xlint -Xlint:-serial +license.file=../LICENSE-2.0.txt +nbm.homepage=http://www.sleuthkit.org/autopsy/ +nbm.needs.restart=true +spec.version.base=1.2 From eb82122a0947c73128b793237ea67d7aad4b6c4c Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Mon, 11 Nov 2013 13:44:56 -0500 Subject: [PATCH 5/9] Only show full path for certain artifact nodes. --- .../datamodel/BlackboardArtifactNode.java | 49 ++++++++++++++----- 1 file changed, 37 insertions(+), 12 deletions(-) diff --git a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java index 168494b1a9..27caebc469 100644 --- a/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java +++ b/Core/src/org/sleuthkit/autopsy/datamodel/BlackboardArtifactNode.java @@ -19,6 +19,7 @@ package org.sleuthkit.autopsy.datamodel; import java.util.ArrayList; +import java.util.Arrays; import java.util.LinkedHashMap; import java.util.List; import java.util.Map; @@ -45,6 +46,15 @@ public class BlackboardArtifactNode extends DisplayableItemNode { private Content associated; private List customProperties; static final Logger logger = Logger.getLogger(BlackboardArtifactNode.class.getName()); + /** + * Artifact types which should have the associated content's full unique path + * as a property. + */ + private static final Integer[] SHOW_UNIQUE_PATH = new Integer[] { + BlackboardArtifact.ARTIFACT_TYPE.TSK_HASHSET_HIT.getTypeID(), + BlackboardArtifact.ARTIFACT_TYPE.TSK_KEYWORD_HIT.getTypeID(), + BlackboardArtifact.ARTIFACT_TYPE.TSK_TAG_FILE.getTypeID(), + }; /** * Construct blackboard artifact node from an artifact and using provided @@ -99,18 +109,6 @@ public class BlackboardArtifactNode extends DisplayableItemNode { "Source File", NO_DESCR, associated.getName())); - - String sourcePath = ""; - try { - sourcePath = associated.getUniquePath(); - } catch (TskCoreException ex) { - logger.log(Level.WARNING, "Failed to get unique path from: " + associated.getName()); - } - - if (sourcePath.isEmpty() == false) { - ss.put(new NodeProperty("File Path", "File Path", - NO_DESCR, sourcePath)); - } for (Map.Entry entry : map.entrySet()) { ss.put(new NodeProperty(entry.getKey(), @@ -125,6 +123,33 @@ public class BlackboardArtifactNode extends DisplayableItemNode { ss.put(np); } } + final int artifactTypeId = artifact.getArtifactTypeID(); + + if (Arrays.asList(SHOW_UNIQUE_PATH).contains(artifactTypeId)) { + String sourcePath = ""; + try { + sourcePath = associated.getUniquePath(); + } catch (TskCoreException ex) { + logger.log(Level.WARNING, "Failed to get unique path from: " + associated.getName()); + } + + if (sourcePath.isEmpty() == false) { + ss.put(new NodeProperty("File Path", "File Path", + NO_DESCR, sourcePath)); + } + } else { + String dataSource = ""; + try { + dataSource = associated.getImage().getName(); + } catch (TskCoreException ex) { + logger.log(Level.WARNING, "Failed to get image name from " + associated.getName()); + } + + if (dataSource.isEmpty() == false) { + ss.put(new NodeProperty("Data Source", "Data Source", + NO_DESCR, dataSource)); + } + } return s; } From 6f336add8ea25ddf50731da921aa3f9988c58572 Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Thu, 14 Nov 2013 16:48:39 -0500 Subject: [PATCH 6/9] Fixed View in new Window action for images. --- .../autopsy/directorytree/NewWindowViewAction.java | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java b/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java index 32fba54b80..01535a00cf 100644 --- a/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java +++ b/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java @@ -22,6 +22,7 @@ package org.sleuthkit.autopsy.directorytree; import java.awt.event.ActionEvent; import java.util.logging.Level; import javax.swing.AbstractAction; +import javax.swing.SwingUtilities; import org.openide.nodes.Node; import org.openide.windows.Mode; import org.openide.windows.WindowManager; @@ -63,12 +64,18 @@ public class NewWindowViewAction extends AbstractAction{ } } - DataContentTopComponent dctc = DataContentTopComponent.createUndocked(name, this.contentNode); + final DataContentTopComponent dctc = DataContentTopComponent.createUndocked(name, null); Mode m = WindowManager.getDefault().findMode("outputFloat"); m.dockInto(dctc); dctc.open(); + SwingUtilities.invokeLater(new Runnable() { + @Override + public void run() { + dctc.setNode(contentNode); + } + }); } From b4a8640669c420ad682655ec7bb6f79307740c84 Mon Sep 17 00:00:00 2001 From: Jeff Wallace Date: Thu, 14 Nov 2013 16:50:02 -0500 Subject: [PATCH 7/9] Added documentation to the fix. --- .../sleuthkit/autopsy/directorytree/NewWindowViewAction.java | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java b/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java index 01535a00cf..f65aaf4506 100644 --- a/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java +++ b/Core/src/org/sleuthkit/autopsy/directorytree/NewWindowViewAction.java @@ -70,6 +70,8 @@ public class NewWindowViewAction extends AbstractAction{ m.dockInto(dctc); dctc.open(); + // Queue setting the node on the EDT thread to be done later so the dctc + // can completely initialize. SwingUtilities.invokeLater(new Runnable() { @Override public void run() { From 3a570965565b2a8c2b8c0fa73c13e468af691c4d Mon Sep 17 00:00:00 2001 From: Brian Carrier Date: Thu, 14 Nov 2013 21:40:56 -0500 Subject: [PATCH 8/9] normalized web attributes, reworded keyword ingest labels --- .../autopsy/report/ReportGenerator.java | 8 +- .../hashdatabase/HashDbIngestModule.java | 3 +- .../autopsy/keywordsearch/Bundle.properties | 182 +++++++++--------- .../docs/keywordsearch-about.html | 162 ++++++++-------- .../autopsy/recentactivity/Chrome.java | 9 +- .../autopsy/recentactivity/ExtractIE.java | 6 +- .../autopsy/recentactivity/Firefox.java | 10 +- 7 files changed, 186 insertions(+), 194 deletions(-) diff --git a/Core/src/org/sleuthkit/autopsy/report/ReportGenerator.java b/Core/src/org/sleuthkit/autopsy/report/ReportGenerator.java index 56f4f8780f..e0a8c486fe 100644 --- a/Core/src/org/sleuthkit/autopsy/report/ReportGenerator.java +++ b/Core/src/org/sleuthkit/autopsy/report/ReportGenerator.java @@ -830,13 +830,13 @@ public class ReportGenerator { switch (type) { case TSK_WEB_BOOKMARK: - columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"URL", "Title", "Date Accessed", "Program", "Source File"})); + columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"URL", "Title", "Date Created", "Program", "Source File"})); break; case TSK_WEB_COOKIE: columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"URL", "Date/Time", "Name", "Value", "Program", "Source File"})); break; case TSK_WEB_HISTORY: - columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"URL", "Date Accessed", "Referrer", "Name", "Program", "Source File"})); + columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"URL", "Date Accessed", "Referrer", "Title", "Program", "Source File"})); break; case TSK_WEB_DOWNLOAD: columnHeaders = new ArrayList<>(Arrays.asList(new String[] {"Destination", "Source URL", "Date Accessed", "Program", "Source File"})); @@ -997,7 +997,7 @@ public class ReportGenerator { List bookmark = new ArrayList<>(); bookmark.add(attributes.get(ATTRIBUTE_TYPE.TSK_URL.getTypeID())); bookmark.add(attributes.get(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID())); - bookmark.add(attributes.get(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID())); + bookmark.add(attributes.get(ATTRIBUTE_TYPE.TSK_DATETIME_CREATED.getTypeID())); bookmark.add(attributes.get(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID())); bookmark.add(getFileUniquePath(artifactData.getObjectID())); return bookmark; @@ -1015,7 +1015,7 @@ public class ReportGenerator { history.add(attributes.get(ATTRIBUTE_TYPE.TSK_URL.getTypeID())); history.add(attributes.get(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID())); history.add(attributes.get(ATTRIBUTE_TYPE.TSK_REFERRER.getTypeID())); - history.add(attributes.get(ATTRIBUTE_TYPE.TSK_NAME.getTypeID())); + history.add(attributes.get(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID())); history.add(attributes.get(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID())); history.add(getFileUniquePath(artifactData.getObjectID())); return history; diff --git a/HashDatabase/src/org/sleuthkit/autopsy/hashdatabase/HashDbIngestModule.java b/HashDatabase/src/org/sleuthkit/autopsy/hashdatabase/HashDbIngestModule.java index 49e81d60bf..6cdb4764c1 100644 --- a/HashDatabase/src/org/sleuthkit/autopsy/hashdatabase/HashDbIngestModule.java +++ b/HashDatabase/src/org/sleuthkit/autopsy/hashdatabase/HashDbIngestModule.java @@ -271,7 +271,7 @@ public class HashDbIngestModule extends IngestModuleAbstractFile { detailsSb.append(""); services.postMessage(IngestMessage.createDataMessage(++messageId, this, - "Notable: " + abstractFile.getName(), + "Known Bad: " + abstractFile.getName(), detailsSb.toString(), abstractFile.getName() + md5Hash, badFile)); @@ -280,7 +280,6 @@ public class HashDbIngestModule extends IngestModuleAbstractFile { } catch (TskException ex) { logger.log(Level.WARNING, "Error creating blackboard artifact", ex); } - } private ProcessResult processFile(AbstractFile file) { diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties index 65dbef957c..1bfc26e95b 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties @@ -1,91 +1,91 @@ -OpenIDE-Module-Display-Category=Ingest Module -OpenIDE-Module-Long-Description=\ - Keyword Search ingest module.\n\n\ - The module indexes files found in the disk image at ingest time. \ - It 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 seach bar in the top-right corner, extracted text viewer and search results viewer showing highlighted keywords found. -OpenIDE-Module-Name=KeywordSearch -ListBundleName=Keyword Lists -ListBundleConfig=Keyword List Configuration -IndexProgressPanel.statusText.text=Status text -IndexProgressPanel.cancelButton.text=Cancel -ExtractedContentPanel.hitLabel.text=Matches on page: -ExtractedContentPanel.hitCountLabel.text=- -ExtractedContentPanel.hitOfLabel.text=of -ExtractedContentPanel.hitTotalLabel.text=- -ExtractedContentPanel.hitButtonsLabel.text=Match -ExtractedContentPanel.hitPreviousButton.text= -ExtractedContentPanel.hitNextButton.text= -ExtractedContentPanel.copyMenuItem.text=Copy -ExtractedContentPanel.selectAllMenuItem.text=Select All -KeywordSearchEditListPanel.saveListButton.text=Copy List -KeywordSearchEditListPanel.addWordField.text= -KeywordSearchEditListPanel.addWordButton.text=Add -KeywordSearchEditListPanel.chRegex.text=Regular Expression -KeywordSearchEditListPanel.deleteWordButton.text=Remove Selected -KeywordSearchEditListPanel.cutMenuItem.text=Cut -KeywordSearchEditListPanel.selectAllMenuItem.text=Select All -KeywordSearchEditListPanel.pasteMenuItem.text=Paste -KeywordSearchEditListPanel.copyMenuItem.text=Copy -KeywordSearchEditListPanel.exportButton.text=Export List -KeywordSearchEditListPanel.deleteListButton.text=Delete List -KeywordSearchListsManagementPanel.newListButton.text=New List -KeywordSearchEditListPanel.useForIngestCheckbox.text=Enable for ingest -KeywordSearchListsManagementPanel.importButton.text=Import List -KeywordSearchPanel.searchBox.text=Search... -KeywordSearchPanel.regExCheckboxMenuItem.text=Use Regular Expressions -KeywordSearchPanel.settingsLabel.text= -KeywordSearchListsViewerPanel.searchAddButton.text=Search -KeywordSearchListsViewerPanel.manageListsButton.text=Manage Lists -KeywordSearchListsViewerPanel.ingestIndexLabel.text=Files Indexed: -KeywordSearchEditListPanel.selectorsCombo.toolTipText=Regular Expression selector type (optional) -KeywordSearchPanel.searchButton.text= -KeywordSearchPanel.cutMenuItem.text=Cut -KeywordSearchPanel.copyMenuItem.text=Copy -KeywordSearchPanel.pasteMenuItem.text=Paste -KeywordSearchPanel.selectAllMenuItem.text=Select All -ExtractedContentPanel.pageButtonsLabel.text=Page -ExtractedContentPanel.pageNextButton.text= -ExtractedContentPanel.pagePreviousButton.actionCommand=pagePreviousButton -ExtractedContentPanel.pagePreviousButton.text= -ExtractedContentPanel.pagesLabel.text=Page: -ExtractedContentPanel.pageOfLabel.text=of -ExtractedContentPanel.pageCurLabel.text=- -ExtractedContentPanel.pageTotalLabel.text=- -ExtractedContentPanel.hitLabel.toolTipText= -KeywordSearchEditListPanel.ingestMessagesCheckbox.text=Enable sending messages to inbox during ingest -KeywordSearchEditListPanel.ingestMessagesCheckbox.toolTipText=Send messages during triage / ingest when hits on keyword from this list occur -KeywordSearchConfigurationPanel2.skipNSRLCheckBox.text=Do not add files in NSRL (known files) to keyword index during ingest -KeywordSearchConfigurationPanel2.skipNSRLCheckBox.toolTipText=Requires Hash DB service to had run previously, or be selected for next ingest. -KeywordSearchConfigurationPanel2.filesIndexedValue.text=- -KeywordSearchConfigurationPanel2.filesIndexedLabel.text=Files in keyword index: -KeywordSearchIngestSimplePanel.languagesLabel.text=Scripts enabled for string extraction from unknown file types: -KeywordSearchIngestSimplePanel.languagesValLabel.text=- -KeywordSearchIngestSimplePanel.languagesLabel.toolTipText=Scripts enabled for string extraction from unknown file types. Changes can be done in Advanced Settings. -KeywordSearchIngestSimplePanel.languagesValLabel.toolTipText= -KeywordSearchConfigurationPanel3.languagesLabel.text=Enabled scripts (languages): -KeywordSearchConfigurationPanel2.chunksLabel.text=Chunks in keyword index: -KeywordSearchConfigurationPanel2.chunksValLabel.text=- -KeywordSearchConfigurationPanel3.enableUTF8Checkbox.text=Enable UTF8 text extraction -KeywordSearchConfigurationPanel3.enableUTF16Checkbox.text=Enable UTF16LE and UTF16BE string extraction -KeywordSearchEditListPanel.keywordOptionsLabel.text=Keyword Options -KeywordSearchEditListPanel.listOptionsLabel.text=List Options -KeywordSearchConfigurationPanel3.ingestSettingsLabel.text=Ingest settings for string extraction from unknown file types (changes effective on next ingest): -KeywordSearchConfigurationPanel2.settingsLabel.text=Settings -KeywordSearchConfigurationPanel2.informationLabel.text=Information -KeywordSearchListsManagementPanel.keywordListsLabel.text=Keyword Lists: -KeywordSearchEditListPanel.keywordsLabel.text=Keywords: -KeywordSearchConfigurationPanel2.timeRadioButton1.toolTipText=20 mins. (fastest ingest time) -KeywordSearchConfigurationPanel2.timeRadioButton1.text=20 minutes (slowest feedback, fastest ingest) -KeywordSearchConfigurationPanel2.timeRadioButton2.toolTipText=10 minutes (faster overall ingest time than default) -KeywordSearchConfigurationPanel2.timeRadioButton2.text=10 minutes (slower feedback, faster ingest) -KeywordSearchConfigurationPanel2.timeRadioButton3.toolTipText=5 minutes (overall ingest time will be longer) -KeywordSearchConfigurationPanel2.timeRadioButton3.text=5 minutes (default) -KeywordSearchIngestSimplePanel.encodingsLabel.text=Encodings: -KeywordSearchIngestSimplePanel.keywordSearchEncodings.text=- -KeywordSearchIngestSimplePanel.titleLabel.text=Select keyword lists to enable during ingest: -OpenIDE-Module-Short-Description=Keyword Search ingest module, extracted text viewer and keyword search tools -KeywordSearchListsViewerPanel.manageListsButton.toolTipText=Manage keyword lists, their settings and associated keywords. The settings are shared among all cases. -KeywordSearchConfigurationPanel2.frequencyLabel.text=Results update frequency during ingest: -KeywordSearchConfigurationPanel2.timeRadioButton4.text_1=1 minute (faster feedback, longest ingest) -KeywordSearchConfigurationPanel2.timeRadioButton4.toolTipText=1 minute (overall ingest time will be longest) +OpenIDE-Module-Display-Category=Ingest Module +OpenIDE-Module-Long-Description=\ + Keyword Search ingest module.\n\n\ + The module indexes files found in the disk image at ingest time. \ + It 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 seach bar in the top-right corner, extracted text viewer and search results viewer showing highlighted keywords found. +OpenIDE-Module-Name=KeywordSearch +ListBundleName=Keyword Lists +ListBundleConfig=Keyword List Configuration +IndexProgressPanel.statusText.text=Status text +IndexProgressPanel.cancelButton.text=Cancel +ExtractedContentPanel.hitLabel.text=Matches on page: +ExtractedContentPanel.hitCountLabel.text=- +ExtractedContentPanel.hitOfLabel.text=of +ExtractedContentPanel.hitTotalLabel.text=- +ExtractedContentPanel.hitButtonsLabel.text=Match +ExtractedContentPanel.hitPreviousButton.text= +ExtractedContentPanel.hitNextButton.text= +ExtractedContentPanel.copyMenuItem.text=Copy +ExtractedContentPanel.selectAllMenuItem.text=Select All +KeywordSearchEditListPanel.saveListButton.text=Copy List +KeywordSearchEditListPanel.addWordField.text= +KeywordSearchEditListPanel.addWordButton.text=Add +KeywordSearchEditListPanel.chRegex.text=Regular Expression +KeywordSearchEditListPanel.deleteWordButton.text=Remove Selected +KeywordSearchEditListPanel.cutMenuItem.text=Cut +KeywordSearchEditListPanel.selectAllMenuItem.text=Select All +KeywordSearchEditListPanel.pasteMenuItem.text=Paste +KeywordSearchEditListPanel.copyMenuItem.text=Copy +KeywordSearchEditListPanel.exportButton.text=Export List +KeywordSearchEditListPanel.deleteListButton.text=Delete List +KeywordSearchListsManagementPanel.newListButton.text=New List +KeywordSearchEditListPanel.useForIngestCheckbox.text=Use during ingest +KeywordSearchListsManagementPanel.importButton.text=Import List +KeywordSearchPanel.searchBox.text=Search... +KeywordSearchPanel.regExCheckboxMenuItem.text=Use Regular Expressions +KeywordSearchPanel.settingsLabel.text= +KeywordSearchListsViewerPanel.searchAddButton.text=Search +KeywordSearchListsViewerPanel.manageListsButton.text=Manage Lists +KeywordSearchListsViewerPanel.ingestIndexLabel.text=Files Indexed: +KeywordSearchEditListPanel.selectorsCombo.toolTipText=Regular Expression selector type (optional) +KeywordSearchPanel.searchButton.text= +KeywordSearchPanel.cutMenuItem.text=Cut +KeywordSearchPanel.copyMenuItem.text=Copy +KeywordSearchPanel.pasteMenuItem.text=Paste +KeywordSearchPanel.selectAllMenuItem.text=Select All +ExtractedContentPanel.pageButtonsLabel.text=Page +ExtractedContentPanel.pageNextButton.text= +ExtractedContentPanel.pagePreviousButton.actionCommand=pagePreviousButton +ExtractedContentPanel.pagePreviousButton.text= +ExtractedContentPanel.pagesLabel.text=Page: +ExtractedContentPanel.pageOfLabel.text=of +ExtractedContentPanel.pageCurLabel.text=- +ExtractedContentPanel.pageTotalLabel.text=- +ExtractedContentPanel.hitLabel.toolTipText= +KeywordSearchEditListPanel.ingestMessagesCheckbox.text=Send messages to inbox during ingest +KeywordSearchEditListPanel.ingestMessagesCheckbox.toolTipText=Send messages during ingest when hits on keyword from this list occur +KeywordSearchConfigurationPanel2.skipNSRLCheckBox.text=Do not add files in NSRL (known files) to keyword index during ingest +KeywordSearchConfigurationPanel2.skipNSRLCheckBox.toolTipText=Requires Hash DB service to had run previously, or be selected for next ingest. +KeywordSearchConfigurationPanel2.filesIndexedValue.text=- +KeywordSearchConfigurationPanel2.filesIndexedLabel.text=Files in keyword index: +KeywordSearchIngestSimplePanel.languagesLabel.text=Scripts enabled for string extraction from unknown file types: +KeywordSearchIngestSimplePanel.languagesValLabel.text=- +KeywordSearchIngestSimplePanel.languagesLabel.toolTipText=Scripts enabled for string extraction from unknown file types. Changes can be done in Advanced Settings. +KeywordSearchIngestSimplePanel.languagesValLabel.toolTipText= +KeywordSearchConfigurationPanel3.languagesLabel.text=Enabled scripts (languages): +KeywordSearchConfigurationPanel2.chunksLabel.text=Chunks in keyword index: +KeywordSearchConfigurationPanel2.chunksValLabel.text=- +KeywordSearchConfigurationPanel3.enableUTF8Checkbox.text=Enable UTF8 text extraction +KeywordSearchConfigurationPanel3.enableUTF16Checkbox.text=Enable UTF16LE and UTF16BE string extraction +KeywordSearchEditListPanel.keywordOptionsLabel.text=Keyword Options +KeywordSearchEditListPanel.listOptionsLabel.text=List Options +KeywordSearchConfigurationPanel3.ingestSettingsLabel.text=Ingest settings for string extraction from unknown file types (changes effective on next ingest): +KeywordSearchConfigurationPanel2.settingsLabel.text=Settings +KeywordSearchConfigurationPanel2.informationLabel.text=Information +KeywordSearchListsManagementPanel.keywordListsLabel.text=Keyword Lists: +KeywordSearchEditListPanel.keywordsLabel.text=Keywords: +KeywordSearchConfigurationPanel2.timeRadioButton1.toolTipText=20 mins. (fastest ingest time) +KeywordSearchConfigurationPanel2.timeRadioButton1.text=20 minutes (slowest feedback, fastest ingest) +KeywordSearchConfigurationPanel2.timeRadioButton2.toolTipText=10 minutes (faster overall ingest time than default) +KeywordSearchConfigurationPanel2.timeRadioButton2.text=10 minutes (slower feedback, faster ingest) +KeywordSearchConfigurationPanel2.timeRadioButton3.toolTipText=5 minutes (overall ingest time will be longer) +KeywordSearchConfigurationPanel2.timeRadioButton3.text=5 minutes (default) +KeywordSearchIngestSimplePanel.encodingsLabel.text=Encodings: +KeywordSearchIngestSimplePanel.keywordSearchEncodings.text=- +KeywordSearchIngestSimplePanel.titleLabel.text=Select keyword lists to enable during ingest: +OpenIDE-Module-Short-Description=Keyword Search ingest module, extracted text viewer and keyword search tools +KeywordSearchListsViewerPanel.manageListsButton.toolTipText=Manage keyword lists, their settings and associated keywords. The settings are shared among all cases. +KeywordSearchConfigurationPanel2.frequencyLabel.text=Results update frequency during ingest: +KeywordSearchConfigurationPanel2.timeRadioButton4.text_1=1 minute (faster feedback, longest ingest) +KeywordSearchConfigurationPanel2.timeRadioButton4.toolTipText=1 minute (overall ingest time will be longest) diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/docs/keywordsearch-about.html b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/docs/keywordsearch-about.html index ec2a45f056..a283f09dde 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/docs/keywordsearch-about.html +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/docs/keywordsearch-about.html @@ -1,81 +1,81 @@ - - - - - Keyword Search - - - - -

Keyword Search

-

- Autopsy ships a keyword search module, which provides the ingest capability - and also supports a manual text search mode. -

-

The keyword search ingest module extracts text from the files on the image being ingested and adds them to the index that can then be searched.

-

- Autopsy tries its best to extract maximum amount of text from the files being indexed. - First, the indexing will try to extract text from supported file formats, such as pure text file format, MS Office Documents, PDF files, Email files, and many others. - If the file is not supported by the standard text extractor, Autopsy will fallback to string extraction algorithm. - String extraction on unknown file formats or arbitrary binary files can often still extract a good amount of text from the file, often good enough to provide additional clues. - However, string extraction will not be able to extract text strings from binary files that have been encrypted. -

-

- Autopsy ships with some built-in lists that define regular expressions and enable user to search for Phone Numbers, IP addresses, URLs and E-mail addresses. - However, enabling some of these very general lists can produce a very large number of hits, many of them can be false-positives. -

-

- Once files are in the index, they can be searched quickly for specific keywords, regular expressions, - or using keyword search lists that can contain a mixture of keywords and regular expressions. - Search queries can be executed automatically by the ingest during the ingest run, or at the end of the ingest, depending on the current settings and the time it takes to ingest the image. -

-

Search queries can also be executed manually by the user at any time, as long as there are some files already indexed and ready to be searched.

-

- Keyword search module will save the search results regardless whether the search is performed by the ingest process, or manually by the user. - The saved results are available in the Directory Tree in the left hand side panel. -

-

- To see keyword search results in real-time while ingest is running, add keyword lists using the - Keyword Search Configuration Dialog - and select the "Use during ingest" check box. - You can select "Enable sending messages to inbox during ingest" per list, if the hits on that list should be reported in the Inbox, which is recommended for very specific searches. -

-

- See (Ingest) - for more information on ingest in general. -

-

- Once there are files in the index, the Keyword Search Bar - will be available for use to manually search at any time. -

- - - + + + + + Keyword Search + + + + +

Keyword Search

+

+ Autopsy ships a keyword search module, which provides the ingest capability + and also supports a manual text search mode. +

+

The keyword search ingest module extracts text from the files on the image being ingested and adds them to the index that can then be searched.

+

+ Autopsy tries its best to extract maximum amount of text from the files being indexed. + First, the indexing will try to extract text from supported file formats, such as pure text file format, MS Office Documents, PDF files, Email files, and many others. + If the file is not supported by the standard text extractor, Autopsy will fallback to string extraction algorithm. + String extraction on unknown file formats or arbitrary binary files can often still extract a good amount of text from the file, often good enough to provide additional clues. + However, string extraction will not be able to extract text strings from binary files that have been encrypted. +

+

+ Autopsy ships with some built-in lists that define regular expressions and enable user to search for Phone Numbers, IP addresses, URLs and E-mail addresses. + However, enabling some of these very general lists can produce a very large number of hits, many of them can be false-positives. +

+

+ Once files are in the index, they can be searched quickly for specific keywords, regular expressions, + or using keyword search lists that can contain a mixture of keywords and regular expressions. + Search queries can be executed automatically by the ingest during the ingest run, or at the end of the ingest, depending on the current settings and the time it takes to ingest the image. +

+

Search queries can also be executed manually by the user at any time, as long as there are some files already indexed and ready to be searched.

+

+ Keyword search module will save the search results regardless whether the search is performed by the ingest process, or manually by the user. + The saved results are available in the Directory Tree in the left hand side panel. +

+

+ To see keyword search results in real-time while ingest is running, add keyword lists using the + Keyword Search Configuration Dialog + and select the "Use during ingest" check box. + You can select "Send messages to inbox during ingest" per list, if the hits on that list should be reported in the Inbox, which is recommended for very specific searches. +

+

+ See (Ingest) + for more information on ingest in general. +

+

+ Once there are files in the index, the Keyword Search Bar + will be available for use to manually search at any time. +

+ + + diff --git a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Chrome.java b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Chrome.java index c405e92fda..849aae992e 100644 --- a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Chrome.java +++ b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Chrome.java @@ -150,12 +150,9 @@ public class Chrome extends Extract { Collection bbattributes = new ArrayList(); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "Recent Activity", ((result.get("url").toString() != null) ? result.get("url").toString() : ""))); - //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL_DECODED.getTypeID(), "Recent Activity", ((result.get("url").toString() != null) ? EscapeUtil.decodeURL(result.get("url").toString()) : ""))); - //TODO Revisit usage of deprecated constructor per TSK-583 - //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_LAST_ACCESSED.getTypeID(), "Recent Activity", "Last Visited", ((Long.valueOf(result.get("last_visit_time").toString())) / 10000000))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "Recent Activity", ((Long.valueOf(result.get("last_visit_time").toString())) / 10000000))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_REFERRER.getTypeID(), "Recent Activity", ((result.get("from_visit").toString() != null) ? result.get("from_visit").toString() : ""))); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_NAME.getTypeID(), "Recent Activity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID(), "Recent Activity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "Recent Activity", "Chrome")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "Recent Activity", (Util.extractDomain((result.get("url").toString() != null) ? result.get("url").toString() : "")))); this.addArtifact(ARTIFACT_TYPE.TSK_WEB_HISTORY, historyFile, bbattributes); @@ -276,8 +273,8 @@ public class Chrome extends Extract { //TODO Revisit usage of deprecated constructor as per TSK-583 //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_LAST_ACCESSED.getTypeID(), "Recent Activity", "Last Visited", (date / 10000000))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "Recent Activity", url)); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_NAME.getTypeID(), "Recent Activity", name)); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "Recent Activity", (date / 10000000))); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID(), "Recent Activity", name)); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_CREATED.getTypeID(), "Recent Activity", (date / 10000000))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "Recent Activity", "Chrome")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "Recent Activity", domain)); bbart.addAttributes(bbattributes); diff --git a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractIE.java b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractIE.java index dc3920ab8e..980c48aba4 100644 --- a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractIE.java +++ b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractIE.java @@ -157,8 +157,8 @@ public class ExtractIE extends Extract { Collection bbattributes = new ArrayList(); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "RecentActivity", url)); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_NAME.getTypeID(), "RecentActivity", name)); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "RecentActivity", datetime)); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID(), "RecentActivity", name)); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_CREATED.getTypeID(), "RecentActivity", datetime)); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "RecentActivity", "Internet Explorer")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "RecentActivity", domain)); this.addArtifact(ARTIFACT_TYPE.TSK_WEB_BOOKMARK, favoritesFile, bbattributes); @@ -507,7 +507,7 @@ public class ExtractIE extends Extract { bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "RecentActivity", ftime)); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_REFERRER.getTypeID(), "RecentActivity", "")); - // @@@ NOte that other browser modules are adding NAME in hre for the title + // @@@ NOte that other browser modules are adding TITLE in hre for the title bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "RecentActivity", "Internet Explorer")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "RecentActivity", domain)); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_USER_NAME.getTypeID(), "RecentActivity", user)); diff --git a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Firefox.java b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Firefox.java index b558cc9a26..4a207ac8b6 100644 --- a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Firefox.java +++ b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/Firefox.java @@ -132,11 +132,9 @@ public class Firefox extends Extract { Collection bbattributes = new ArrayList(); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "RecentActivity", ((result.get("url").toString() != null) ? result.get("url").toString() : ""))); //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL_DECODED.getTypeID(), "RecentActivity", ((result.get("url").toString() != null) ? EscapeUtil.decodeURL(result.get("url").toString()) : ""))); - //TODO Revisit usage of deprecated constructor as per TSK-583 - //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_LAST_ACCESSED.getTypeID(), "RecentActivity", "Last Visited", (Long.valueOf(result.get("visit_date").toString())))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "RecentActivity", (Long.valueOf(result.get("visit_date").toString())))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_REFERRER.getTypeID(), "RecentActivity", ((result.get("ref").toString() != null) ? result.get("ref").toString() : ""))); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_NAME.getTypeID(), "RecentActivity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID(), "RecentActivity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "RecentActivity", "FireFox")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "RecentActivity", (Util.extractDomain((result.get("url").toString() != null) ? result.get("url").toString() : "")))); this.addArtifact(ARTIFACT_TYPE.TSK_WEB_HISTORY, historyFile, bbattributes); @@ -199,8 +197,8 @@ public class Firefox extends Extract { Collection bbattributes = new ArrayList(); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "RecentActivity", ((result.get("url").toString() != null) ? result.get("url").toString() : ""))); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_NAME.getTypeID(), "RecentActivity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); - bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "RecentActivity", (Long.valueOf(result.get("dateAdded").toString())))); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_TITLE.getTypeID(), "RecentActivity", ((result.get("title").toString() != null) ? result.get("title").toString() : ""))); + bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_CREATED.getTypeID(), "RecentActivity", (Long.valueOf(result.get("dateAdded").toString())))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_PROG_NAME.getTypeID(), "RecentActivity", "FireFox")); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DOMAIN.getTypeID(), "RecentActivity", (Util.extractDomain((result.get("url").toString() != null) ? result.get("url").toString() : "")))); this.addArtifact(ARTIFACT_TYPE.TSK_WEB_BOOKMARK, bookmarkFile, bbattributes); @@ -355,8 +353,6 @@ public class Firefox extends Extract { bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL.getTypeID(), "RecentActivity", ((result.get("source").toString() != null) ? result.get("source").toString() : ""))); //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_URL_DECODED.getTypeID(), "RecentActivity", ((result.get("source").toString() != null) ? EscapeUtil.decodeURL(result.get("source").toString()) : ""))); - //TODO Revisit usage of deprecated constructor as per TSK-583 - //bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_LAST_ACCESSED.getTypeID(), "RecentActivity", "Last Visited", (Long.valueOf(result.get("startTime").toString())))); bbattributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_DATETIME_ACCESSED.getTypeID(), "RecentActivity", (Long.valueOf(result.get("startTime").toString())))); try { From cc85120678c23d9ac26ddb4339a453f19073bb82 Mon Sep 17 00:00:00 2001 From: Brian Carrier Date: Tue, 19 Nov 2013 13:36:53 -0500 Subject: [PATCH 9/9] normalized line endings --- test/README.txt | 26 +- test/script/Emailer.py | 98 +- test/script/regression.py | 3708 ++++++++--------- test/script/srcupdater.py | 374 +- thunderbirdparser/manifest.mf | 14 +- .../nbproject/project.properties | 12 +- update_versions.py | 1878 ++++----- 7 files changed, 3055 insertions(+), 3055 deletions(-) diff --git a/test/README.txt b/test/README.txt index d0064b4f95..854f5e1a33 100644 --- a/test/README.txt +++ b/test/README.txt @@ -1,13 +1,13 @@ -This folder contains the data and scripts required to run regression tests -for Autopsy. There is a 'Testing' folder in the root directory that contains -the Java code that drives Autopsy to perform the tests. - -To run these tests: -- You will need python3. We run this from within Cygwin. -- Download the input images by typing 'ant test-download-imgs' in the root Autopsy folder. - This will place images in 'test/input'. -- Run 'python3 regression.py' from inside of the 'test/scripts' folder. -- Alternatively, run 'python3 regression.py -l [CONFIGFILE] to run the tests on a specified - list of images using a configuration file. See config.xml in the 'test/scripts' folder to - see configuration file formatting. -- Run 'python3 regression.py -h' to see other options. +This folder contains the data and scripts required to run regression tests +for Autopsy. There is a 'Testing' folder in the root directory that contains +the Java code that drives Autopsy to perform the tests. + +To run these tests: +- You will need python3. We run this from within Cygwin. +- Download the input images by typing 'ant test-download-imgs' in the root Autopsy folder. + This will place images in 'test/input'. +- Run 'python3 regression.py' from inside of the 'test/scripts' folder. +- Alternatively, run 'python3 regression.py -l [CONFIGFILE] to run the tests on a specified + list of images using a configuration file. See config.xml in the 'test/scripts' folder to + see configuration file formatting. +- Run 'python3 regression.py -h' to see other options. diff --git a/test/script/Emailer.py b/test/script/Emailer.py index 5d12e6afa3..7e661e12ea 100644 --- a/test/script/Emailer.py +++ b/test/script/Emailer.py @@ -1,49 +1,49 @@ -import smtplib -from email.mime.image import MIMEImage -from email.mime.multipart import MIMEMultipart -from email.mime.text import MIMEText -from email.mime.base import MIMEBase -from email import encoders -import xml -from xml.dom.minidom import parse, parseString - -def send_email(to, server, subj, body, attachments): - """Send an email with the given information. - - Args: - to: a String, the email address to send the email to - server: a String, the mail server to send from - subj: a String, the subject line of the message - body: a String, the body of the message - attachments: a listof_pathto_File, the attachements to include - """ - msg = MIMEMultipart() - msg['Subject'] = subj - # me == the sender's email address - # family = the list of all recipients' email addresses - msg['From'] = 'AutopsyTest' - msg['To'] = to - msg.preamble = 'This is a test' - container = MIMEText(body, 'plain') - msg.attach(container) - Build_email(msg, attachments) - s = smtplib.SMTP(server) - try: - print('Sending Email') - s.sendmail(msg['From'], msg['To'], msg.as_string()) - except Exception as e: - print(str(e)) - s.quit() - -def Build_email(msg, attachments): - for file in attachments: - part = MIMEBase('application', "octet-stream") - atach = open(file, "rb") - attch = atach.read() - noml = file.split("\\") - nom = noml[len(noml)-1] - part.set_payload(attch) - encoders.encode_base64(part) - part.add_header('Content-Disposition', 'attachment; filename="' + nom + '"') - msg.attach(part) - +import smtplib +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart +from email.mime.text import MIMEText +from email.mime.base import MIMEBase +from email import encoders +import xml +from xml.dom.minidom import parse, parseString + +def send_email(to, server, subj, body, attachments): + """Send an email with the given information. + + Args: + to: a String, the email address to send the email to + server: a String, the mail server to send from + subj: a String, the subject line of the message + body: a String, the body of the message + attachments: a listof_pathto_File, the attachements to include + """ + msg = MIMEMultipart() + msg['Subject'] = subj + # me == the sender's email address + # family = the list of all recipients' email addresses + msg['From'] = 'AutopsyTest' + msg['To'] = to + msg.preamble = 'This is a test' + container = MIMEText(body, 'plain') + msg.attach(container) + Build_email(msg, attachments) + s = smtplib.SMTP(server) + try: + print('Sending Email') + s.sendmail(msg['From'], msg['To'], msg.as_string()) + except Exception as e: + print(str(e)) + s.quit() + +def Build_email(msg, attachments): + for file in attachments: + part = MIMEBase('application', "octet-stream") + atach = open(file, "rb") + attch = atach.read() + noml = file.split("\\") + nom = noml[len(noml)-1] + part.set_payload(attch) + encoders.encode_base64(part) + part.add_header('Content-Disposition', 'attachment; filename="' + nom + '"') + msg.attach(part) + diff --git a/test/script/regression.py b/test/script/regression.py index b2ad319963..6c640823ed 100644 --- a/test/script/regression.py +++ b/test/script/regression.py @@ -1,1854 +1,1854 @@ -#!/usr/bin/python -# -*- coding: utf_8 -*- - - # Autopsy Forensic Browser - # - # Copyright 2013 Basis Technology Corp. - # - # 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. -from tskdbdiff import TskDbDiff, TskDbDiffException -import codecs -import datetime -import logging -import os -import re -import shutil -import socket -import sqlite3 -import subprocess -import sys -from sys import platform as _platform -import time -import traceback -import xml -from time import localtime, strftime -from xml.dom.minidom import parse, parseString -import smtplib -from email.mime.image import MIMEImage -from email.mime.multipart import MIMEMultipart -from email.mime.text import MIMEText -import re -import zipfile -import zlib -import Emailer -import srcupdater -from regression_utils import * - -# -# Please read me... -# -# This is the regression testing Python script. -# It uses an ant command to run build.xml for RegressionTest.java -# -# The code is cleanly sectioned and commented. -# Please follow the current formatting. -# It is a long and potentially confusing script. -# -# Variable, function, and class names are written in Python conventions: -# this_is_a_variable this_is_a_function() ThisIsAClass -# -# - - -# Data Definitions: -# -# pathto_X: A path to type X. -# ConfigFile: An XML file formatted according to the template in myconfig.xml -# ParsedConfig: A dom object that represents a ConfigFile -# SQLCursor: A cursor recieved from a connection to an SQL database -# Nat: A Natural Number -# Image: An image -# - -# Enumeration of database types used for the simplification of generating database paths -DBType = enum('OUTPUT', 'GOLD', 'BACKUP') - -# Common filename of the output and gold databases (although they are in different directories -DB_FILENAME = "autopsy.db" - -# Backup database filename -BACKUP_DB_FILENAME = "autopsy_backup.db" - -# TODO: Double check this purpose statement -# Folder name for gold standard database testing -AUTOPSY_TEST_CASE = "AutopsyTestCase" - -# TODO: Double check this purpose statement -# The filename of the log to store error messages -COMMON_LOG = "AutopsyErrors.txt" - -Day = 0 - -#----------------------# -# Main # -#----------------------# -def main(): - """Parse the command-line arguments, create the configuration, and run the tests.""" - args = Args() - parse_result = args.parse() - test_config = TestConfiguration(args) - # The arguments were given wrong: - if not parse_result: - return - if(not args.fr): - antin = ["ant"] - antin.append("-f") - antin.append(os.path.join("..","..","build.xml")) - antin.append("test-download-imgs") - if SYS is OS.CYGWIN: - subprocess.call(antin) - elif SYS is OS.WIN: - theproc = subprocess.Popen(antin, shell = True, stdout=subprocess.PIPE) - theproc.communicate() - # Otherwise test away! - TestRunner.run_tests(test_config) - - -class TestRunner(object): - """A collection of functions to run the regression tests.""" - - def run_tests(test_config): - """Run the tests specified by the main TestConfiguration. - - Executes the AutopsyIngest for each image and dispatches the results based on - the mode (rebuild or testing) - """ - test_data_list = [ TestData(image, test_config) for image in test_config.images ] - - Reports.html_add_images(test_config.html_log, test_config.images) - - logres =[] - for test_data in test_data_list: - Errors.clear_print_logs() - Errors.set_testing_phase(test_data.image) - if not (test_config.args.rebuild or os.path.exists(test_data.gold_archive)): - msg = "Gold standard doesn't exist, skipping image:" - Errors.print_error(msg) - Errors.print_error(test_data.gold_archive) - continue - TestRunner._run_autopsy_ingest(test_data) - - if test_config.args.rebuild: - TestRunner.rebuild(test_data) - else: - logres.append(TestRunner._run_test(test_data)) - test_data.printout = Errors.printout - test_data.printerror = Errors.printerror - - Reports.write_html_foot(test_config.html_log) - # TODO: move this elsewhere - if (len(logres)>0): - for lm in logres: - for ln in lm: - Errors.add_email_msg(ln) - - # TODO: possibly worth putting this in a sub method - if all([ test_data.overall_passed for test_data in test_data_list ]): - Errors.add_email_msg("All images passed.\n") - else: - msg = "The following images failed:\n" - for test_data in test_data_list: - if not test_data.overall_passed: - msg += "\t" + test_data.image + "\n" - Errors.add_email_msg(msg) - html = open(test_config.html_log) - Errors.add_email_attachment(html.name) - html.close() - - if test_config.email_enabled: - Emailer.send_email(test_config.mail_to, test_config.mail_server, - test_config.mail_subject, Errors.email_body, Errors.email_attachs) - - def _run_autopsy_ingest(test_data): - """Run Autopsy ingest for the image in the given TestData. - - Also generates the necessary logs for rebuilding or diff. - - Args: - test_data: the TestData to run the ingest on. - """ - if image_type(test_data.image_file) == IMGTYPE.UNKNOWN: - Errors.print_error("Error: Image type is unrecognized:") - Errors.print_error(test_data.image_file + "\n") - return - - logging.debug("--------------------") - logging.debug(test_data.image_name) - logging.debug("--------------------") - TestRunner._run_ant(test_data) - time.sleep(2) # Give everything a second to process - - try: - # Dump the database before we diff or use it for rebuild - TskDbDiff.dump_output_db(test_data.get_db_path(DBType.OUTPUT), test_data.get_db_dump_path(DBType.OUTPUT), - test_data.get_sorted_data_path(DBType.OUTPUT)) - except sqlite3.OperationalError as e: - print("Ingest did not run properly.", - "Make sure no other instances of Autopsy are open and try again.") - sys.exit() - - # merges logs into a single log for later diff / rebuild - copy_logs(test_data) - Logs.generate_log_data(test_data) - - TestRunner._handle_solr(test_data) - TestRunner._handle_exception(test_data) - - #TODO: figure out return type of _run_test (logres) - def _run_test(test_data): - """Compare the results of the output to the gold standard. - - Args: - test_data: the TestData - - Returns: - logres? - """ - TestRunner._extract_gold(test_data) - - # Look for core exceptions - # @@@ Should be moved to TestResultsDiffer, but it didn't know about logres -- need to look into that - logres = Logs.search_common_log("TskCoreException", test_data) - - TestResultsDiffer.run_diff(test_data) - test_data.overall_passed = (test_data.html_report_passed and - test_data.errors_diff_passed and test_data.db_diff_passed) - - Reports.generate_reports(test_data) - if(not test_data.overall_passed): - Errors.add_email_attachment(test_data.common_log_path) - return logres - - def _extract_gold(test_data): - """Extract gold archive file to output/gold/tmp/ - - Args: - test_data: the TestData - """ - extrctr = zipfile.ZipFile(test_data.gold_archive, 'r', compression=zipfile.ZIP_DEFLATED) - extrctr.extractall(test_data.main_config.gold) - extrctr.close - time.sleep(2) - - def _handle_solr(test_data): - """Clean up SOLR index if in keep mode (-k). - - Args: - test_data: the TestData - """ - if not test_data.main_config.args.keep: - if clear_dir(test_data.solr_index): - print_report([], "DELETE SOLR INDEX", "Solr index deleted.") - else: - print_report([], "KEEP SOLR INDEX", "Solr index has been kept.") - - def _handle_exception(test_data): - """If running in exception mode, print exceptions to log. - - Args: - test_data: the TestData - """ - if test_data.main_config.args.exception: - exceptions = search_logs(test_data.main_config.args.exception_string, test_data) - okay = ("No warnings or exceptions found containing text '" + - test_data.main_config.args.exception_string + "'.") - print_report(exceptions, "EXCEPTION", okay) - - def rebuild(test_data): - """Rebuild the gold standard with the given TestData. - - Copies the test-generated database and html report files into the gold directory. - """ - test_config = test_data.main_config - # Errors to print - errors = [] - # Delete the current gold standards - gold_dir = test_config.img_gold - clear_dir(test_config.img_gold) - tmpdir = make_path(gold_dir, test_data.image_name) - dbinpth = test_data.get_db_path(DBType.OUTPUT) - dboutpth = make_path(tmpdir, DB_FILENAME) - dataoutpth = make_path(tmpdir, test_data.image_name + "SortedData.txt") - dbdumpinpth = test_data.get_db_dump_path(DBType.OUTPUT) - dbdumpoutpth = make_path(tmpdir, test_data.image_name + "DBDump.txt") - if not os.path.exists(test_config.img_gold): - os.makedirs(test_config.img_gold) - if not os.path.exists(tmpdir): - os.makedirs(tmpdir) - try: - shutil.copy(dbinpth, dboutpth) - if file_exists(test_data.get_sorted_data_path(DBType.OUTPUT)): - shutil.copy(test_data.get_sorted_data_path(DBType.OUTPUT), dataoutpth) - shutil.copy(dbdumpinpth, dbdumpoutpth) - error_pth = make_path(tmpdir, test_data.image_name+"SortedErrors.txt") - shutil.copy(test_data.sorted_log, error_pth) - except IOError as e: - Errors.print_error(str(e)) - Errors.add_email_message("Not rebuilt properly") - print(str(e)) - print(traceback.format_exc()) - # Rebuild the HTML report - output_html_report_dir = test_data.get_html_report_path(DBType.OUTPUT) - gold_html_report_dir = make_path(tmpdir, "Report") - - try: - shutil.copytree(output_html_report_dir, gold_html_report_dir) - except OSError as e: - errors.append(e.error()) - except Exception as e: - errors.append("Error: Unknown fatal error when rebuilding the gold html report.") - errors.append(str(e) + "\n") - print(traceback.format_exc()) - oldcwd = os.getcwd() - zpdir = gold_dir - os.chdir(zpdir) - os.chdir("..") - img_gold = "tmp" - img_archive = make_path(test_data.image_name+"-archive.zip") - comprssr = zipfile.ZipFile(img_archive, 'w',compression=zipfile.ZIP_DEFLATED) - TestRunner.zipdir(img_gold, comprssr) - comprssr.close() - os.chdir(oldcwd) - del_dir(test_config.img_gold) - okay = "Sucessfully rebuilt all gold standards." - print_report(errors, "REBUILDING", okay) - - def zipdir(path, zip): - for root, dirs, files in os.walk(path): - for file in files: - zip.write(os.path.join(root, file)) - - def _run_ant(test_data): - """Construct and run the ant build command for the given TestData. - - Tests Autopsy by calling RegressionTest.java via the ant build file. - - Args: - test_data: the TestData - """ - test_config = test_data.main_config - # Set up the directories - if dir_exists(test_data.output_path): - shutil.rmtree(test_data.output_path) - os.makedirs(test_data.output_path) - test_data.ant = ["ant"] - test_data.ant.append("-v") - test_data.ant.append("-f") - # case.ant.append(case.build_path) - test_data.ant.append(os.path.join("..","..","Testing","build.xml")) - test_data.ant.append("regression-test") - test_data.ant.append("-l") - test_data.ant.append(test_data.antlog_dir) - test_data.ant.append("-Dimg_path=" + test_data.image_file) - test_data.ant.append("-Dknown_bad_path=" + test_config.known_bad_path) - test_data.ant.append("-Dkeyword_path=" + test_config.keyword_path) - test_data.ant.append("-Dnsrl_path=" + test_config.nsrl_path) - test_data.ant.append("-Dgold_path=" + test_config.gold) - test_data.ant.append("-Dout_path=" + - make_local_path(test_data.output_path)) - test_data.ant.append("-Dignore_unalloc=" + "%s" % test_config.args.unallocated) - test_data.ant.append("-Dtest.timeout=" + str(test_config.timeout)) - - Errors.print_out("Ingesting Image:\n" + test_data.image_file + "\n") - Errors.print_out("CMD: " + " ".join(test_data.ant)) - Errors.print_out("Starting test...\n") - antoutpth = make_local_path(test_data.main_config.output_dir, "antRunOutput.txt") - antout = open(antoutpth, "a") - if SYS is OS.CYGWIN: - subprocess.call(test_data.ant, stdout=subprocess.PIPE) - elif SYS is OS.WIN: - theproc = subprocess.Popen(test_data.ant, shell = True, stdout=subprocess.PIPE) - theproc.communicate() - antout.close() - - -class TestData(object): - """Container for the input and output of a single image. - - Represents data for the test of a single image, including path to the image, - database paths, etc. - - Attributes: - main_config: the global TestConfiguration - ant: a listof_String, the ant command for this TestData - image_file: a pathto_Image, the image for this TestData - image: a String, the image file's name - image_name: a String, the image file's name with a trailing (0) - output_path: pathto_Dir, the output directory for this TestData - autopsy_data_file: a pathto_File, the IMAGE_NAMEAutopsy_data.txt file - warning_log: a pathto_File, the AutopsyLogs.txt file - antlog_dir: a pathto_File, the antlog.txt file - test_dbdump: a pathto_File, the database dump, IMAGENAMEDump.txt - common_log_path: a pathto_File, the IMAGE_NAMECOMMON_LOG file - sorted_log: a pathto_File, the IMAGENAMESortedErrors.txt file - reports_dir: a pathto_Dir, the AutopsyTestCase/Reports folder - gold_data_dir: a pathto_Dir, the gold standard directory - gold_archive: a pathto_File, the gold standard archive - logs_dir: a pathto_Dir, the location where autopsy logs are stored - solr_index: a pathto_Dir, the locatino of the solr index - html_report_passed: a boolean, did the HTML report diff pass? - errors_diff_passed: a boolean, did the error diff pass? - db_diff_passed: a boolean, did the db diff pass? - overall_passed: a boolean, did the test pass? - total_test_time: a String representation of the test duration - start_date: a String representation of this TestData's start date - end_date: a String representation of the TestData's end date - total_ingest_time: a String representation of the total ingest time - artifact_count: a Nat, the number of artifacts - artifact_fail: a Nat, the number of artifact failures - heap_space: a String representation of TODO - service_times: a String representation of TODO - autopsy_version: a String, the version of autopsy that was run - ingest_messages: a Nat, the number of ingest messages - indexed_files: a Nat, the number of files indexed during the ingest - indexed_chunks: a Nat, the number of chunks indexed during the ingest - printerror: a listof_String, the error messages printed during this TestData's test - printout: a listof_String, the messages pritned during this TestData's test - """ - - def __init__(self, image, main_config): - """Init this TestData with it's image and the test configuration. - - Args: - image: the Image to be tested. - main_config: the global TestConfiguration. - """ - # Configuration Data - self.main_config = main_config - self.ant = [] - self.image_file = str(image) - # TODO: This 0 should be be refactored out, but it will require rebuilding and changing of outputs. - self.image = get_image_name(self.image_file) - self.image_name = self.image + "(0)" - # Directory structure and files - self.output_path = make_path(self.main_config.output_dir, self.image_name) - self.autopsy_data_file = make_path(self.output_path, self.image_name + "Autopsy_data.txt") - self.warning_log = make_local_path(self.output_path, "AutopsyLogs.txt") - self.antlog_dir = make_local_path(self.output_path, "antlog.txt") - self.test_dbdump = make_path(self.output_path, self.image_name + - "DBDump.txt") - self.common_log_path = make_local_path(self.output_path, self.image_name + COMMON_LOG) - self.sorted_log = make_local_path(self.output_path, self.image_name + "SortedErrors.txt") - self.reports_dir = make_path(self.output_path, AUTOPSY_TEST_CASE, "Reports") - self.gold_data_dir = make_path(self.main_config.img_gold, self.image_name) - self.gold_archive = make_path(self.main_config.gold, - self.image_name + "-archive.zip") - self.logs_dir = make_path(self.output_path, "logs") - self.solr_index = make_path(self.output_path, AUTOPSY_TEST_CASE, - "ModuleOutput", "KeywordSearch") - # Results and Info - self.html_report_passed = False - self.errors_diff_passed = False - self.db_diff_passed = False - self.overall_passed = False - # Ingest info - self.total_test_time = "" - self.start_date = "" - self.end_date = "" - self.total_ingest_time = "" - self.artifact_count = 0 - self.artifact_fail = 0 - self.heap_space = "" - self.service_times = "" - self.autopsy_version = "" - self.ingest_messages = 0 - self.indexed_files = 0 - self.indexed_chunks = 0 - # Error tracking - self.printerror = [] - self.printout = [] - - def ant_to_string(self): - string = "" - for arg in self.ant: - string += (arg + " ") - return string - - def get_db_path(self, db_type): - """Get the path to the database file that corresponds to the given DBType. - - Args: - DBType: the DBType of the path to be generated. - """ - if(db_type == DBType.GOLD): - db_path = make_path(self.gold_data_dir, DB_FILENAME) - elif(db_type == DBType.OUTPUT): - db_path = make_path(self.main_config.output_dir, self.image_name, AUTOPSY_TEST_CASE, DB_FILENAME) - else: - db_path = make_path(self.main_config.output_dir, self.image_name, AUTOPSY_TEST_CASE, BACKUP_DB_FILENAME) - return db_path - - def get_html_report_path(self, html_type): - """Get the path to the HTML Report folder that corresponds to the given DBType. - - Args: - DBType: the DBType of the path to be generated. - """ - if(html_type == DBType.GOLD): - return make_path(self.gold_data_dir, "Report") - else: - # Autopsy creates an HTML report folder in the form AutopsyTestCase DATE-TIME - # It's impossible to get the exact time the folder was created, but the folder - # we are looking for is the only one in the self.reports_dir folder - html_path = "" - for fs in os.listdir(self.reports_dir): - html_path = make_path(self.reports_dir, fs) - if os.path.isdir(html_path): - break - return make_path(html_path, os.listdir(html_path)[0]) - - def get_sorted_data_path(self, file_type): - """Get the path to the SortedData file that corresponds to the given DBType. - - Args: - file_type: the DBType of the path to be generated - """ - return self._get_path_to_file(file_type, "SortedData.txt") - - def get_sorted_errors_path(self, file_type): - """Get the path to the SortedErrors file that correspodns to the given - DBType. - - Args: - file_type: the DBType of the path to be generated - """ - return self._get_path_to_file(file_type, "SortedErrors.txt") - - def get_db_dump_path(self, file_type): - """Get the path to the DBDump file that corresponds to the given DBType. - - Args: - file_type: the DBType of the path to be generated - """ - return self._get_path_to_file(file_type, "DBDump.txt") - - def _get_path_to_file(self, file_type, file_name): - """Get the path to the specified file with the specified type. - - Args: - file_type: the DBType of the path to be generated - file_name: a String, the filename of the path to be generated - """ - full_filename = self.image_name + file_name - if(file_type == DBType.GOLD): - return make_path(self.gold_data_dir, full_filename) - else: - return make_path(self.output_path, full_filename) - - -class TestConfiguration(object): - """Container for test configuration data. - - The Master Test Configuration. Encapsulates consolidated high level input from - config XML file and command-line arguments. - - Attributes: - args: an Args, the command line arguments - output_dir: a pathto_Dir, the output directory - input_dir: a pathto_Dir, the input directory - gold: a pathto_Dir, the gold directory - img_gold: a pathto_Dir, the temp directory where gold images are unzipped to - csv: a pathto_File, the local csv file - global_csv: a pathto_File, the global csv file - html_log: a pathto_File - known_bad_path: - keyword_path: - nsrl_path: - build_path: a pathto_File, the ant build file which runs the tests - autopsy_version: - ingest_messages: a Nat, number of ingest messages - indexed_files: a Nat, the number of indexed files - indexed_chunks: a Nat, the number of indexed chunks - timer: - images: a listof_Image, the images to be tested - timeout: a Nat, the amount of time before killing the test - ant: a listof_String, the ant command to run the tests - """ - - def __init__(self, args): - """Inits TestConfiguration and loads a config file if available. - - Args: - args: an Args, the command line arguments. - """ - self.args = args - # Paths: - self.output_dir = "" - self.input_dir = make_local_path("..","input") - self.gold = make_path("..", "output", "gold") - self.img_gold = make_path(self.gold, 'tmp') - # Logs: - self.csv = "" - self.global_csv = "" - self.html_log = "" - # Ant info: - self.known_bad_path = make_path(self.input_dir, "notablehashes.txt-md5.idx") - self.keyword_path = make_path(self.input_dir, "notablekeywords.xml") - self.nsrl_path = make_path(self.input_dir, "nsrl.txt-md5.idx") - self.build_path = make_path("..", "build.xml") - # Infinite Testing info - timer = 0 - self.images = [] - # Email info - self.email_enabled = args.email_enabled - self.mail_server = "" - self.mail_to = "" - self.mail_subject = "" - # Set the timeout to something huge - # The entire tester should not timeout before this number in ms - # However it only seems to take about half this time - # And it's very buggy, so we're being careful - self.timeout = 24 * 60 * 60 * 1000 * 1000 - - if not self.args.single: - self._load_config_file(self.args.config_file) - else: - self.images.append(self.args.single_file) - self._init_logs() - #self._init_imgs() - #self._init_build_info() - - - def _load_config_file(self, config_file): - """Updates this TestConfiguration's attributes from the config file. - - Initializes this TestConfiguration by iterating through the XML config file - command-line argument. Populates self.images and optional email configuration - - Args: - config_file: ConfigFile - the configuration file to load - """ - try: - count = 0 - parsed_config = parse(config_file) - logres = [] - counts = {} - if parsed_config.getElementsByTagName("indir"): - self.input_dir = parsed_config.getElementsByTagName("indir")[0].getAttribute("value").encode().decode("utf_8") - if parsed_config.getElementsByTagName("global_csv"): - self.global_csv = parsed_config.getElementsByTagName("global_csv")[0].getAttribute("value").encode().decode("utf_8") - self.global_csv = make_local_path(self.global_csv) - if parsed_config.getElementsByTagName("golddir"): - self.gold = parsed_config.getElementsByTagName("golddir")[0].getAttribute("value").encode().decode("utf_8") - self.img_gold = make_path(self.gold, 'tmp') - - self._init_imgs(parsed_config) - self._init_build_info(parsed_config) - self._init_email_info(parsed_config) - - except IOError as e: - msg = "There was an error loading the configuration file.\n" - msg += "\t" + str(e) - Errors.add_email_msg(msg) - logging.critical(traceback.format_exc()) - print(traceback.format_exc()) - - def _init_logs(self): - """Setup output folder, logs, and reporting infrastructure.""" - if(not dir_exists(make_path("..", "output", "results"))): - os.makedirs(make_path("..", "output", "results",)) - self.output_dir = make_path("..", "output", "results", time.strftime("%Y.%m.%d-%H.%M.%S")) - os.makedirs(self.output_dir) - self.csv = make_local_path(self.output_dir, "CSV.txt") - self.html_log = make_path(self.output_dir, "AutopsyTestCase.html") - log_name = self.output_dir + "\\regression.log" - logging.basicConfig(filename=log_name, level=logging.DEBUG) - - def _init_build_info(self, parsed_config): - """Initializes paths that point to information necessary to run the AutopsyIngest.""" - build_elements = parsed_config.getElementsByTagName("build") - if build_elements: - build_element = build_elements[0] - build_path = build_element.getAttribute("value").encode().decode("utf_8") - self.build_path = build_path - - def _init_imgs(self, parsed_config): - """Initialize the list of images to run tests on.""" - for element in parsed_config.getElementsByTagName("image"): - value = element.getAttribute("value").encode().decode("utf_8") - print ("Image in Config File: " + value) - if file_exists(value): - self.images.append(value) - else: - msg = "File: " + value + " doesn't exist" - Errors.print_error(msg) - Errors.add_email_msg(msg) - image_count = len(self.images) - - # Sanity check to see if there are obvious gold images that we are not testing - gold_count = 0 - for file in os.listdir(self.gold): - if not(file == 'tmp'): - gold_count+=1 - - if (image_count > gold_count): - print("******Alert: There are more input images than gold standards, some images will not be properly tested.\n") - elif (image_count < gold_count): - print("******Alert: There are more gold standards than input images, this will not check all gold Standards.\n") - - def _init_email_info(self, parsed_config): - """Initializes email information dictionary""" - email_elements = parsed_config.getElementsByTagName("email") - if email_elements: - mail_to = email_elements[0] - self.mail_to = mail_to.getAttribute("value").encode().decode("utf_8") - mail_server_elements = parsed_config.getElementsByTagName("mail_server") - if mail_server_elements: - mail_from = mail_server_elements[0] - self.mail_server = mail_from.getAttribute("value").encode().decode("utf_8") - subject_elements = parsed_config.getElementsByTagName("subject") - if subject_elements: - subject = subject_elements[0] - self.mail_subject = subject.getAttribute("value").encode().decode("utf_8") - if self.mail_server and self.mail_to and self.args.email_enabled: - self.email_enabled = True - print("Email will be sent to ", self.mail_to) - else: - print("No email will be sent.") - - -#-------------------------------------------------# -# Functions relating to comparing outputs # -#-------------------------------------------------# -class TestResultsDiffer(object): - """Compares results for a single test.""" - - def run_diff(test_data): - """Compares results for a single test. - - Args: - test_data: the TestData to use. - databaseDiff: TskDbDiff object created based off test_data - """ - try: - output_db = test_data.get_db_path(DBType.OUTPUT) - gold_db = test_data.get_db_path(DBType.GOLD) - output_dir = test_data.output_path - gold_bb_dump = test_data.get_sorted_data_path(DBType.GOLD) - gold_dump = test_data.get_db_dump_path(DBType.GOLD) - test_data.db_diff_pass = all(TskDbDiff(output_db, gold_db, output_dir=output_dir, gold_bb_dump=gold_bb_dump, - gold_dump=gold_dump).run_diff()) - - # Compare Exceptions - # replace is a fucntion that replaces strings of digits with 'd' - # this is needed so dates and times will not cause the diff to fail - replace = lambda file: re.sub(re.compile("\d"), "d", file) - output_errors = test_data.get_sorted_errors_path(DBType.OUTPUT) - gold_errors = test_data.get_sorted_errors_path(DBType.GOLD) - passed = TestResultsDiffer._compare_text(output_errors, gold_errors, - replace) - test_data.errors_diff_passed = passed - - # Compare html output - gold_report_path = test_data.get_html_report_path(DBType.GOLD) - output_report_path = test_data.get_html_report_path(DBType.OUTPUT) - passed = TestResultsDiffer._html_report_diff(gold_report_path, - output_report_path) - test_data.html_report_passed = passed - - # Clean up tmp folder - del_dir(test_data.gold_data_dir) - - except sqlite3.OperationalError as e: - Errors.print_error("Tests failed while running the diff:\n") - Errors.print_error(str(e)) - except TskDbDiffException as e: - Errors.print_error(str(e)) - except Exception as e: - Errors.print_error("Tests failed due to an error, try rebuilding or creating gold standards.\n") - Errors.print_error(str(e) + "\n") - print(traceback.format_exc()) - - def _compare_text(output_file, gold_file, process=None): - """Compare two text files. - - Args: - output_file: a pathto_File, the output text file - gold_file: a pathto_File, the input text file - pre-process: (optional) a function of String -> String that will be - called on each input file before the diff, if specified. - """ - if(not file_exists(output_file)): - return False - output_data = codecs.open(output_file, "r", "utf_8").read() - gold_data = codecs.open(gold_file, "r", "utf_8").read() - - if process is not None: - output_data = process(output_data) - gold_data = process(gold_data) - - if (not(gold_data == output_data)): - diff_path = os.path.splitext(os.path.basename(output_file))[0] - diff_path += "-Diff.txt" - diff_file = codecs.open(diff_path, "wb", "utf_8") - dffcmdlst = ["diff", output_file, gold_file] - subprocess.call(dffcmdlst, stdout = diff_file) - Errors.add_email_attachment(diff_path) - msg = "There was a difference in " - msg += os.path.basename(output_file) + ".\n" - Errors.add_email_msg(msg) - Errors.print_error(msg) - return False - else: - return True - - def _html_report_diff(gold_report_path, output_report_path): - """Compare the output and gold html reports. - - Args: - gold_report_path: a pathto_Dir, the gold HTML report directory - output_report_path: a pathto_Dir, the output HTML report directory - - Returns: - true, if the reports match, false otherwise. - """ - try: - gold_html_files = get_files_by_ext(gold_report_path, ".html") - output_html_files = get_files_by_ext(output_report_path, ".html") - - #ensure both reports have the same number of files and are in the same order - if(len(gold_html_files) != len(output_html_files)): - msg = "The reports did not have the same number or files." - msg += "One of the reports may have been corrupted." - Errors.print_error(msg) - else: - gold_html_files.sort() - output_html_files.sort() - - total = {"Gold": 0, "New": 0} - for gold, output in zip(gold_html_files, output_html_files): - count = TestResultsDiffer._compare_report_files(gold, output) - total["Gold"] += count[0] - total["New"] += count[1] - - okay = "The test report matches the gold report." - errors=["Gold report had " + str(total["Gold"]) +" errors", "New report had " + str(total["New"]) + " errors."] - print_report(errors, "REPORT COMPARISON", okay) - - if total["Gold"] == total["New"]: - return True - else: - Errors.print_error("The reports did not match each other.\n " + errors[0] +" and the " + errors[1]) - return False - except OSError as e: - e.print_error() - return False - except Exception as e: - Errors.print_error("Error: Unknown fatal error comparing reports.") - Errors.print_error(str(e) + "\n") - logging.critical(traceback.format_exc()) - return False - - def _compare_report_files(a_path, b_path): - """Compares the two specified report html files. - - Args: - a_path: a pathto_File, the first html report file - b_path: a pathto_File, the second html report file - - Returns: - a tuple of (Nat, Nat), which represent the length of each - unordered list in the html report files, or (0, 0) if the - lenghts are the same. - """ - a_file = open(a_path) - b_file = open(b_path) - a = a_file.read() - b = b_file.read() - a = a[a.find("
    "):] - b = b[b.find("
      "):] - - a_list = TestResultsDiffer._split(a, 50) - b_list = TestResultsDiffer._split(b, 50) - if not len(a_list) == len(b_list): - ex = (len(a_list), len(b_list)) - return ex - else: - return (0, 0) - - # Split a string into an array of string of the given size - def _split(input, size): - return [input[start:start+size] for start in range(0, len(input), size)] - - -class Reports(object): - def generate_reports(test_data): - """Generate the reports for a single test - - Args: - test_data: the TestData - """ - Reports._generate_html(test_data) - if test_data.main_config.global_csv: - Reports._generate_csv(test_data.main_config.global_csv, test_data) - else: - Reports._generate_csv(test_data.main_config.csv, test_data) - - def _generate_html(test_data): - """Generate the HTML log file.""" - # If the file doesn't exist yet, this is the first test_config to run for - # this test, so we need to make the start of the html log - html_log = test_data.main_config.html_log - if not file_exists(html_log): - Reports.write_html_head() - with open(html_log, "a") as html: - # The image title - title = "

      " + test_data.image_name + " \ - tested on " + socket.gethostname() + "

      \ -

      \ - Errors and Warnings |\ - Information |\ - General Output |\ - Logs\ -

      " - # The script errors found - if not test_data.overall_passed: - ids = 'errors1' - else: - ids = 'errors' - errors = "
      \ -

      Errors and Warnings

      \ -
      " - # For each error we have logged in the test_config - for error in test_data.printerror: - # Replace < and > to avoid any html display errors - errors += "

      " + error.replace("<", "<").replace(">", ">") + "

      " - # If there is a \n, we probably want a
      in the html - if "\n" in error: - errors += "
      " - errors += "
      " - - # Links to the logs - logs = "
      \ -

      Logs

      \ -
      " - logs_path = test_data.logs_dir - for file in os.listdir(logs_path): - logs += "

      " + file + "

      " - logs += "
      " - - # All the testing information - info = "
      \ -

      Information

      \ -
      \ - " - # The individual elements - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" - info += "" -# info += "" -# info += "" -# info += "" -# info += "" -# info += "" -# info += "" - info += "
      Image Path:" + test_data.image_file + "
      Image Name:" + test_data.image_name + "
      test_config Output Directory:" + test_data.main_config.output_dir + "
      Autopsy Version:" + test_data.autopsy_version + "
      Heap Space:" + test_data.heap_space + "
      Test Start Date:" + test_data.start_date + "
      Test End Date:" + test_data.end_date + "
      Total Test Time:" + test_data.total_test_time + "
      Total Ingest Time:" + test_data.total_ingest_time + "
      Exceptions Count:" + str(len(get_exceptions(test_data))) + "
      Autopsy OutOfMemoryExceptions:" + str(len(search_logs("OutOfMemoryException", test_data))) + "
      Autopsy OutOfMemoryErrors:" + str(len(search_logs("OutOfMemoryError", test_data))) + "
      Tika OutOfMemoryErrors/Exceptions:" + str(Reports._get_num_memory_errors("tika", test_data)) + "
      Solr OutOfMemoryErrors/Exceptions:" + str(Reports._get_num_memory_errors("solr", test_data)) + "
      TskCoreExceptions:" + str(len(search_log_set("autopsy", "TskCoreException", test_data))) + "
      TskDataExceptions:" + str(len(search_log_set("autopsy", "TskDataException", test_data))) + "
      Ingest Messages Count:" + str(test_data.ingest_messages) + "
      Indexed Files Count:" + str(test_data.indexed_files) + "
      Indexed File Chunks Count:" + str(test_data.indexed_chunks) + "
      Out Of Disk Space:\ -

      (will skew other test results)

      		" + str(len(search_log_set("autopsy", "Stopping ingest due to low disk space on disk", test_data))) + "
      TSK Objects Count:" + str(test_data.db_diff_results.output_objs) + "
      Artifacts Count:" + str(test_data.db_diff_results.output_artifacts)+ "
      Attributes Count:" + str(test_data.db_diff_results.output_attrs) + "
      \ -
      " - # For all the general print statements in the test_config - output = "
      \ -

      General Output

      \ -
      " - # For each printout in the test_config's list - for out in test_data.printout: - output += "

      " + out + "

      " - # If there was a \n it probably means we want a
      in the html - if "\n" in out: - output += "
      " - output += "
      " - - html.write(title) - html.write(errors) - html.write(info) - html.write(logs) - html.write(output) - - def write_html_head(html_log): - """Write the top of the HTML log file. - - Args: - html_log: a pathto_File, the global HTML log - """ - with open(str(html_log), "a") as html: - head = "\ - \ - AutopsyTesttest_config Output\ - \ - \ - " - html.write(head) - - def write_html_foot(html_log): - """Write the bottom of the HTML log file. - - Args: - html_log: a pathto_File, the global HTML log - """ - with open(html_log, "a") as html: - head = "" - html.write(head) - - def html_add_images(html_log, full_image_names): - """Add all the image names to the HTML log. - - Args: - full_image_names: a listof_String, each representing an image name - html_log: a pathto_File, the global HTML log - """ - # If the file doesn't exist yet, this is the first test_config to run for - # this test, so we need to make the start of the html log - if not file_exists(html_log): - Reports.write_html_head(html_log) - with open(html_log, "a") as html: - links = [] - for full_name in full_image_names: - name = get_image_name(full_name) - links.append("" + name + "") - html.write("

      " + (" | ".join(links)) + "

      ") - - def _generate_csv(csv_path, test_data): - """Generate the CSV log file""" - # If the CSV file hasn't already been generated, this is the - # first run, and we need to add the column names - if not file_exists(csv_path): - Reports.csv_header(csv_path) - # Now add on the fields to a new row - with open(csv_path, "a") as csv: - # Variables that need to be written - vars = [] - vars.append( test_data.image_file ) - vars.append( test_data.image_name ) - vars.append( test_data.main_config.output_dir ) - vars.append( socket.gethostname() ) - vars.append( test_data.autopsy_version ) - vars.append( test_data.heap_space ) - vars.append( test_data.start_date ) - vars.append( test_data.end_date ) - vars.append( test_data.total_test_time ) - vars.append( test_data.total_ingest_time ) - vars.append( test_data.service_times ) - vars.append( str(len(get_exceptions(test_data))) ) - vars.append( str(Reports._get_num_memory_errors("autopsy", test_data)) ) - vars.append( str(Reports._get_num_memory_errors("tika", test_data)) ) - vars.append( str(Reports._get_num_memory_errors("solr", test_data)) ) - vars.append( str(len(search_log_set("autopsy", "TskCoreException", test_data))) ) - vars.append( str(len(search_log_set("autopsy", "TskDataException", test_data))) ) - vars.append( str(test_data.ingest_messages) ) - vars.append( str(test_data.indexed_files) ) - vars.append( str(test_data.indexed_chunks) ) - vars.append( str(len(search_log_set("autopsy", "Stopping ingest due to low disk space on disk", test_data))) ) -# vars.append( str(test_data.db_diff_results.output_objs) ) -# vars.append( str(test_data.db_diff_results.output_artifacts) ) -# vars.append( str(test_data.db_diff_results.output_objs) ) - vars.append( make_local_path("gold", test_data.image_name, DB_FILENAME) ) -# vars.append( test_data.db_diff_results.get_artifact_comparison() ) -# vars.append( test_data.db_diff_results.get_attribute_comparison() ) - vars.append( make_local_path("gold", test_data.image_name, "standard.html") ) - vars.append( str(test_data.html_report_passed) ) - vars.append( test_data.ant_to_string() ) - # Join it together with a ", " - output = "|".join(vars) - output += "\n" - # Write to the log! - csv.write(output) - - def csv_header(csv_path): - """Generate the CSV column names.""" - with open(csv_path, "w") as csv: - titles = [] - titles.append("Image Path") - titles.append("Image Name") - titles.append("Output test_config Directory") - titles.append("Host Name") - titles.append("Autopsy Version") - titles.append("Heap Space Setting") - titles.append("Test Start Date") - titles.append("Test End Date") - titles.append("Total Test Time") - titles.append("Total Ingest Time") - titles.append("Service Times") - titles.append("Autopsy Exceptions") - titles.append("Autopsy OutOfMemoryErrors/Exceptions") - titles.append("Tika OutOfMemoryErrors/Exceptions") - titles.append("Solr OutOfMemoryErrors/Exceptions") - titles.append("TskCoreExceptions") - titles.append("TskDataExceptions") - titles.append("Ingest Messages Count") - titles.append("Indexed Files Count") - titles.append("Indexed File Chunks Count") - titles.append("Out Of Disk Space") -# titles.append("Tsk Objects Count") -# titles.append("Artifacts Count") -# titles.append("Attributes Count") - titles.append("Gold Database Name") -# titles.append("Artifacts Comparison") -# titles.append("Attributes Comparison") - titles.append("Gold Report Name") - titles.append("Report Comparison") - titles.append("Ant Command Line") - output = "|".join(titles) - output += "\n" - csv.write(output) - - def _get_num_memory_errors(type, test_data): - """Get the number of OutOfMemory errors and Exceptions. - - Args: - type: a String representing the type of log to check. - test_data: the TestData to examine. - """ - return (len(search_log_set(type, "OutOfMemoryError", test_data)) + - len(search_log_set(type, "OutOfMemoryException", test_data))) - -class Logs(object): - - def generate_log_data(test_data): - """Find and handle relevent data from the Autopsy logs. - - Args: - test_data: the TestData whose logs to examine - """ - Logs._generate_common_log(test_data) - try: - Logs._fill_ingest_data(test_data) - except Exception as e: - Errors.print_error("Error: Unknown fatal error when filling test_config data.") - Errors.print_error(str(e) + "\n") - logging.critical(traceback.format_exc()) - # If running in verbose mode (-v) - if test_data.main_config.args.verbose: - errors = Logs._report_all_errors() - okay = "No warnings or errors in any log files." - print_report(errors, "VERBOSE", okay) - - def _generate_common_log(test_data): - """Generate the common log, the log of all exceptions and warnings from - each log file generated by Autopsy. - - Args: - test_data: the TestData to generate a log for - """ - try: - logs_path = test_data.logs_dir - common_log = codecs.open(test_data.common_log_path, "w", "utf_8") - warning_log = codecs.open(test_data.warning_log, "w", "utf_8") - common_log.write("--------------------------------------------------\n") - common_log.write(test_data.image_name + "\n") - common_log.write("--------------------------------------------------\n") - rep_path = make_local_path(test_data.main_config.output_dir) - rep_path = rep_path.replace("\\\\", "\\") - for file in os.listdir(logs_path): - log = codecs.open(make_path(logs_path, file), "r", "utf_8") - for line in log: - line = line.replace(rep_path, "test_data") - if line.startswith("Exception"): - common_log.write(file +": " + line) - elif line.startswith("Error"): - common_log.write(file +": " + line) - elif line.startswith("SEVERE"): - common_log.write(file +":" + line) - else: - warning_log.write(file +": " + line) - log.close() - common_log.write("\n") - common_log.close() - print(test_data.sorted_log) - srtcmdlst = ["sort", test_data.common_log_path, "-o", test_data.sorted_log] - subprocess.call(srtcmdlst) - except (OSError, IOError) as e: - Errors.print_error("Error: Unable to generate the common log.") - Errors.print_error(str(e) + "\n") - Errors.print_error(traceback.format_exc()) - logging.critical(traceback.format_exc()) - - def _fill_ingest_data(test_data): - """Fill the TestDatas variables that require the log files. - - Args: - test_data: the TestData to modify - """ - try: - # Open autopsy.log.0 - log_path = make_path(test_data.logs_dir, "autopsy.log.0") - log = open(log_path) - - # Set the TestData start time based off the first line of autopsy.log.0 - # *** If logging time format ever changes this will break *** - test_data.start_date = log.readline().split(" org.")[0] - - # Set the test_data ending time based off the "create" time (when the file was copied) - test_data.end_date = time.ctime(os.path.getmtime(log_path)) - except IOError as e: - Errors.print_error("Error: Unable to open autopsy.log.0.") - Errors.print_error(str(e) + "\n") - logging.warning(traceback.format_exc()) - # Start date must look like: "Jul 16, 2012 12:57:53 PM" - # End date must look like: "Mon Jul 16 13:02:42 2012" - # *** If logging time format ever changes this will break *** - start = datetime.datetime.strptime(test_data.start_date, "%b %d, %Y %I:%M:%S %p") - end = datetime.datetime.strptime(test_data.end_date, "%a %b %d %H:%M:%S %Y") - test_data.total_test_time = str(end - start) - - try: - # Set Autopsy version, heap space, ingest time, and service times - - version_line = search_logs("INFO: Application name: Autopsy, version:", test_data)[0] - test_data.autopsy_version = get_word_at(version_line, 5).rstrip(",") - - test_data.heap_space = search_logs("Heap memory usage:", test_data)[0].rstrip().split(": ")[1] - - ingest_line = search_logs("Ingest (including enqueue)", test_data)[0] - test_data.total_ingest_time = get_word_at(ingest_line, 6).rstrip() - - message_line = search_log_set("autopsy", "Ingest messages count:", test_data)[0] - test_data.ingest_messages = int(message_line.rstrip().split(": ")[2]) - - files_line = search_log_set("autopsy", "Indexed files count:", test_data)[0] - test_data.indexed_files = int(files_line.rstrip().split(": ")[2]) - - chunks_line = search_log_set("autopsy", "Indexed file chunks count:", test_data)[0] - test_data.indexed_chunks = int(chunks_line.rstrip().split(": ")[2]) - except (OSError, IOError) as e: - Errors.print_error("Error: Unable to find the required information to fill test_config data.") - Errors.print_error(str(e) + "\n") - logging.critical(traceback.format_exc()) - print(traceback.format_exc()) - try: - service_lines = search_log("autopsy.log.0", "to process()", test_data) - service_list = [] - for line in service_lines: - words = line.split(" ") - # Kind of forcing our way into getting this data - # If this format changes, the tester will break - i = words.index("secs.") - times = words[i-4] + " " - times += words[i-3] + " " - times += words[i-2] + " " - times += words[i-1] + " " - times += words[i] - service_list.append(times) - test_data.service_times = "; ".join(service_list) - except (OSError, IOError) as e: - Errors.print_error("Error: Unknown fatal error when finding service times.") - Errors.print_error(str(e) + "\n") - logging.critical(traceback.format_exc()) - - def _report_all_errors(): - """Generate a list of all the errors found in the common log. - - Returns: - a listof_String, the errors found in the common log - """ - try: - return get_warnings() + get_exceptions() - except (OSError, IOError) as e: - Errors.print_error("Error: Unknown fatal error when reporting all errors.") - Errors.print_error(str(e) + "\n") - logging.warning(traceback.format_exc()) - - def search_common_log(string, test_data): - """Search the common log for any instances of a given string. - - Args: - string: the String to search for. - test_data: the TestData that holds the log to search. - - Returns: - a listof_String, all the lines that the string is found on - """ - results = [] - log = codecs.open(test_data.common_log_path, "r", "utf_8") - for line in log: - if string in line: - results.append(line) - log.close() - return results - - -def print_report(errors, name, okay): - """Print a report with the specified information. - - Args: - errors: a listof_String, the errors to report. - name: a String, the name of the report. - okay: the String to print when there are no errors. - """ - if errors: - Errors.print_error("--------< " + name + " >----------") - for error in errors: - Errors.print_error(str(error)) - Errors.print_error("--------< / " + name + " >--------\n") - else: - Errors.print_out("-----------------------------------------------------------------") - Errors.print_out("< " + name + " - " + okay + " />") - Errors.print_out("-----------------------------------------------------------------\n") - - -def get_exceptions(test_data): - """Get a list of the exceptions in the autopsy logs. - - Args: - test_data: the TestData to use to find the exceptions. - Returns: - a listof_String, the exceptions found in the logs. - """ - exceptions = [] - logs_path = test_data.logs_dir - results = [] - for file in os.listdir(logs_path): - if "autopsy.log" in file: - log = codecs.open(make_path(logs_path, file), "r", "utf_8") - ex = re.compile("\SException") - er = re.compile("\SError") - for line in log: - if ex.search(line) or er.search(line): - exceptions.append(line) - log.close() - return exceptions - -def get_warnings(test_data): - """Get a list of the warnings listed in the common log. - - Args: - test_data: the TestData to use to find the warnings - - Returns: - listof_String, the warnings found. - """ - warnings = [] - common_log = codecs.open(test_data.warning_log, "r", "utf_8") - for line in common_log: - if "warning" in line.lower(): - warnings.append(line) - common_log.close() - return warnings - -def copy_logs(test_data): - """Copy the Autopsy generated logs to output directory. - - Args: - test_data: the TestData whose logs will be copied - """ - try: - log_dir = os.path.join("..", "..", "Testing","build","test","qa-functional","work","userdir0","var","log") - shutil.copytree(log_dir, test_data.logs_dir) - except OSError as e: - printerror(test_data,"Error: Failed to copy the logs.") - printerror(test_data,str(e) + "\n") - logging.warning(traceback.format_exc()) - -def setDay(): - global Day - Day = int(strftime("%d", localtime())) - -def getLastDay(): - return Day - -def getDay(): - return int(strftime("%d", localtime())) - -def newDay(): - return getLastDay() != getDay() - -#------------------------------------------------------------# -# Exception classes to manage "acceptable" thrown exceptions # -# versus unexpected and fatal exceptions # -#------------------------------------------------------------# - -class FileNotFoundException(Exception): - """ - If a file cannot be found by one of the helper functions, - they will throw a FileNotFoundException unless the purpose - is to return False. - """ - def __init__(self, file): - self.file = file - self.strerror = "FileNotFoundException: " + file - - def print_error(self): - Errors.print_error("Error: File could not be found at:") - Errors.print_error(self.file + "\n") - - def error(self): - error = "Error: File could not be found at:\n" + self.file + "\n" - return error - -class DirNotFoundException(Exception): - """ - If a directory cannot be found by a helper function, - it will throw this exception - """ - def __init__(self, dir): - self.dir = dir - self.strerror = "DirNotFoundException: " + dir - - def print_error(self): - Errors.print_error("Error: Directory could not be found at:") - Errors.print_error(self.dir + "\n") - - def error(self): - error = "Error: Directory could not be found at:\n" + self.dir + "\n" - return error - - -class Errors: - """A class used to manage error reporting. - - Attributes: - printout: a listof_String, the non-error messages that were printed - printerror: a listof_String, the error messages that were printed - email_body: a String, the body of the report email - email_msg_prefix: a String, the prefix for lines added to the email - email_attchs: a listof_pathto_File, the files to be attached to the - report email - """ - printout = [] - printerror = [] - email_body = "" - email_msg_prefix = "Configuration" - email_attachs = [] - - def set_testing_phase(image_name): - """Change the email message prefix to be the given testing phase. - - Args: - image_name: a String, representing the current image being tested - """ - Errors.email_msg_prefix = image_name - - def print_out(msg): - """Print out an informational message. - - Args: - msg: a String, the message to be printed - """ - print(msg) - Errors.printout.append(msg) - - def print_error(msg): - """Print out an error message. - - Args: - msg: a String, the error message to be printed. - """ - print(msg) - Errors.printerror.append(msg) - - def clear_print_logs(): - """Reset the image-specific attributes of the Errors class.""" - Errors.printout = [] - Errors.printerror = [] - - def add_email_msg(msg): - """Add the given message to the body of the report email. - - Args: - msg: a String, the message to be added to the email - """ - Errors.email_body += Errors.email_msg_prefix + ":" + msg - - def add_email_attachment(path): - """Add the given file to be an attachment for the report email - - Args: - file: a pathto_File, the file to add - """ - Errors.email_attachs.append(path) - - -class DiffResults(object): - """Container for the results of the database diff tests. - - Stores artifact, object, and attribute counts and comparisons generated by - TskDbDiff. - - Attributes: - gold_attrs: a Nat, the number of gold attributes - output_attrs: a Nat, the number of output attributes - gold_objs: a Nat, the number of gold objects - output_objs: a Nat, the number of output objects - artifact_comp: a listof_String, describing the differences - attribute_comp: a listof_String, describing the differences - passed: a boolean, did the diff pass? - """ - def __init__(self, tsk_diff): - """Inits a DiffResults - - Args: - tsk_diff: a TskDBDiff - """ - self.gold_attrs = tsk_diff.gold_attributes - self.output_attrs = tsk_diff.autopsy_attributes - self.gold_objs = tsk_diff.gold_objects - self.output_objs = tsk_diff.autopsy_objects - self.artifact_comp = tsk_diff.artifact_comparison - self.attribute_comp = tsk_diff.attribute_comparison - self.gold_artifacts = len(tsk_diff.gold_artifacts) - self.output_artifacts = len(tsk_diff.autopsy_artifacts) - self.passed = tsk_diff.passed - - def get_artifact_comparison(self): - if not self.artifact_comp: - return "All counts matched" - else: - return "; ".join(self.artifact_comp) - - def get_attribute_comparison(self): - if not self.attribute_comp: - return "All counts matched" - list = [] - for error in self.attribute_comp: - list.append(error) - return ";".join(list) - - -#-------------------------------------------------------------# -# Parses argv and stores booleans to match command line input # -#-------------------------------------------------------------# -class Args(object): - """A container for command line options and arguments. - - Attributes: - single: a boolean indicating whether to run in single file mode - single_file: an Image to run the test on - rebuild: a boolean indicating whether to run in rebuild mode - list: a boolean indicating a config file was specified - unallocated: a boolean indicating unallocated space should be ignored - ignore: a boolean indicating the input directory should be ingnored - keep: a boolean indicating whether to keep the SOLR index - verbose: a boolean indicating whether verbose output should be printed - exeception: a boolean indicating whether errors containing exception - exception_string should be printed - exception_sring: a String representing and exception name - fr: a boolean indicating whether gold standard images will be downloaded - """ - def __init__(self): - self.single = False - self.single_file = "" - self.rebuild = False - self.list = False - self.config_file = "" - self.unallocated = False - self.ignore = False - self.keep = False - self.verbose = False - self.exception = False - self.exception_string = "" - self.fr = False - self.email_enabled = False - - def parse(self): - """Get the command line arguments and parse them.""" - nxtproc = [] - nxtproc.append("python3") - nxtproc.append(sys.argv.pop(0)) - while sys.argv: - arg = sys.argv.pop(0) - nxtproc.append(arg) - if(arg == "-f"): - #try: @@@ Commented out until a more specific except statement is added - arg = sys.argv.pop(0) - print("Running on a single file:") - print(path_fix(arg) + "\n") - self.single = True - self.single_file = path_fix(arg) - #except: - # print("Error: No single file given.\n") - # return False - elif(arg == "-r" or arg == "--rebuild"): - print("Running in rebuild mode.\n") - self.rebuild = True - elif(arg == "-l" or arg == "--list"): - try: - arg = sys.argv.pop(0) - nxtproc.append(arg) - print("Running from configuration file:") - print(arg + "\n") - self.list = True - self.config_file = arg - except: - print("Error: No configuration file given.\n") - return False - elif(arg == "-u" or arg == "--unallocated"): - print("Ignoring unallocated space.\n") - self.unallocated = True - elif(arg == "-k" or arg == "--keep"): - print("Keeping the Solr index.\n") - self.keep = True - elif(arg == "-v" or arg == "--verbose"): - print("Running in verbose mode:") - print("Printing all thrown exceptions.\n") - self.verbose = True - elif(arg == "-e" or arg == "--exception"): - try: - arg = sys.argv.pop(0) - nxtproc.append(arg) - print("Running in exception mode: ") - print("Printing all exceptions with the string '" + arg + "'\n") - self.exception = True - self.exception_string = arg - except: - print("Error: No exception string given.") - elif arg == "-h" or arg == "--help": - print(usage()) - return False - elif arg == "-fr" or arg == "--forcerun": - print("Not downloading new images") - self.fr = True - elif arg == "-e" or arg == "-email": - self.email_enabled = True - else: - print(usage()) - return False - # Return the args were sucessfully parsed - return self._sanity_check() - - def _sanity_check(self): - """Check to make sure there are no conflicting arguments and the - specified files exist. - - Returns: - False if there are conflicting arguments or a specified file does - not exist, True otherwise - """ - if self.single and self.list: - print("Cannot run both from config file and on a single file.") - return False - if self.list: - if not file_exists(self.config_file): - print("Configuration file does not exist at:", - self.config_file) - return False - elif self.single: - if not file_exists(self.single_file): - msg = "Image file does not exist at: " + self.single_file - return False - if (not self.single) and (not self.ignore) and (not self.list): - self.config_file = "config.xml" - if not file_exists(self.config_file): - msg = "Configuration file does not exist at: " + self.config_file - return False - - return True - -#### -# Helper Functions -#### -def search_logs(string, test_data): - """Search through all the known log files for a given string. - - Args: - string: the String to search for. - test_data: the TestData that holds the logs to search. - - Returns: - a listof_String, the lines that contained the given String. - """ - logs_path = test_data.logs_dir - results = [] - for file in os.listdir(logs_path): - log = codecs.open(make_path(logs_path, file), "r", "utf_8") - for line in log: - if string in line: - results.append(line) - log.close() - return results - -def search_log(log, string, test_data): - """Search the given log for any instances of a given string. - - Args: - log: a pathto_File, the log to search in - string: the String to search for. - test_data: the TestData that holds the log to search. - - Returns: - a listof_String, all the lines that the string is found on - """ - logs_path = make_path(test_data.logs_dir, log) - try: - results = [] - log = codecs.open(logs_path, "r", "utf_8") - for line in log: - if string in line: - results.append(line) - log.close() - if results: - return results - except: - raise FileNotFoundException(logs_path) - -# Search through all the the logs of the given type -# Types include autopsy, tika, and solr -def search_log_set(type, string, test_data): - """Search through all logs to the given type for the given string. - - Args: - type: the type of log to search in. - string: the String to search for. - test_data: the TestData containing the logs to search. - - Returns: - a listof_String, the lines on which the String was found. - """ - logs_path = test_data.logs_dir - results = [] - for file in os.listdir(logs_path): - if type in file: - log = codecs.open(make_path(logs_path, file), "r", "utf_8") - for line in log: - if string in line: - results.append(line) - log.close() - return results - - -def clear_dir(dir): - """Clears all files from a directory and remakes it. - - Args: - dir: a pathto_Dir, the directory to clear - """ - try: - if dir_exists(dir): - shutil.rmtree(dir) - os.makedirs(dir) - return True; - except OSError as e: - printerror(test_data,"Error: Cannot clear the given directory:") - printerror(test_data,dir + "\n") - print(str(e)) - return False; - -def del_dir(dir): - """Delete the given directory. - - Args: - dir: a pathto_Dir, the directory to delete - """ - try: - if dir_exists(dir): - shutil.rmtree(dir) - return True; - except: - printerror(test_data,"Error: Cannot delete the given directory:") - printerror(test_data,dir + "\n") - return False; - -def get_file_in_dir(dir, ext): - """Returns the first file in the given directory with the given extension. - - Args: - dir: a pathto_Dir, the directory to search - ext: a String, the extension to search for - - Returns: - pathto_File, the file that was found - """ - try: - for file in os.listdir(dir): - if file.endswith(ext): - return make_path(dir, file) - # If nothing has been found, raise an exception - raise FileNotFoundException(dir) - except: - raise DirNotFoundException(dir) - -def find_file_in_dir(dir, name, ext): - """Find the file with the given name in the given directory. - - Args: - dir: a pathto_Dir, the directory to search - name: a String, the basename of the file to search for - ext: a String, the extension of the file to search for - """ - try: - for file in os.listdir(dir): - if file.startswith(name): - if file.endswith(ext): - return make_path(dir, file) - raise FileNotFoundException(dir) - except: - raise DirNotFoundException(dir) - - -class OS: - LINUX, MAC, WIN, CYGWIN = range(4) - - -if __name__ == "__main__": - global SYS - if _platform == "linux" or _platform == "linux2": - SYS = OS.LINUX - elif _platform == "darwin": - SYS = OS.MAC - elif _platform == "win32": - SYS = OS.WIN - elif _platform == "cygwin": - SYS = OS.CYGWIN - - if SYS is OS.WIN or SYS is OS.CYGWIN: - main() - else: - print("We only support Windows and Cygwin at this time.") +#!/usr/bin/python +# -*- coding: utf_8 -*- + + # Autopsy Forensic Browser + # + # Copyright 2013 Basis Technology Corp. + # + # 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. +from tskdbdiff import TskDbDiff, TskDbDiffException +import codecs +import datetime +import logging +import os +import re +import shutil +import socket +import sqlite3 +import subprocess +import sys +from sys import platform as _platform +import time +import traceback +import xml +from time import localtime, strftime +from xml.dom.minidom import parse, parseString +import smtplib +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart +from email.mime.text import MIMEText +import re +import zipfile +import zlib +import Emailer +import srcupdater +from regression_utils import * + +# +# Please read me... +# +# This is the regression testing Python script. +# It uses an ant command to run build.xml for RegressionTest.java +# +# The code is cleanly sectioned and commented. +# Please follow the current formatting. +# It is a long and potentially confusing script. +# +# Variable, function, and class names are written in Python conventions: +# this_is_a_variable this_is_a_function() ThisIsAClass +# +# + + +# Data Definitions: +# +# pathto_X: A path to type X. +# ConfigFile: An XML file formatted according to the template in myconfig.xml +# ParsedConfig: A dom object that represents a ConfigFile +# SQLCursor: A cursor recieved from a connection to an SQL database +# Nat: A Natural Number +# Image: An image +# + +# Enumeration of database types used for the simplification of generating database paths +DBType = enum('OUTPUT', 'GOLD', 'BACKUP') + +# Common filename of the output and gold databases (although they are in different directories +DB_FILENAME = "autopsy.db" + +# Backup database filename +BACKUP_DB_FILENAME = "autopsy_backup.db" + +# TODO: Double check this purpose statement +# Folder name for gold standard database testing +AUTOPSY_TEST_CASE = "AutopsyTestCase" + +# TODO: Double check this purpose statement +# The filename of the log to store error messages +COMMON_LOG = "AutopsyErrors.txt" + +Day = 0 + +#----------------------# +# Main # +#----------------------# +def main(): + """Parse the command-line arguments, create the configuration, and run the tests.""" + args = Args() + parse_result = args.parse() + test_config = TestConfiguration(args) + # The arguments were given wrong: + if not parse_result: + return + if(not args.fr): + antin = ["ant"] + antin.append("-f") + antin.append(os.path.join("..","..","build.xml")) + antin.append("test-download-imgs") + if SYS is OS.CYGWIN: + subprocess.call(antin) + elif SYS is OS.WIN: + theproc = subprocess.Popen(antin, shell = True, stdout=subprocess.PIPE) + theproc.communicate() + # Otherwise test away! + TestRunner.run_tests(test_config) + + +class TestRunner(object): + """A collection of functions to run the regression tests.""" + + def run_tests(test_config): + """Run the tests specified by the main TestConfiguration. + + Executes the AutopsyIngest for each image and dispatches the results based on + the mode (rebuild or testing) + """ + test_data_list = [ TestData(image, test_config) for image in test_config.images ] + + Reports.html_add_images(test_config.html_log, test_config.images) + + logres =[] + for test_data in test_data_list: + Errors.clear_print_logs() + Errors.set_testing_phase(test_data.image) + if not (test_config.args.rebuild or os.path.exists(test_data.gold_archive)): + msg = "Gold standard doesn't exist, skipping image:" + Errors.print_error(msg) + Errors.print_error(test_data.gold_archive) + continue + TestRunner._run_autopsy_ingest(test_data) + + if test_config.args.rebuild: + TestRunner.rebuild(test_data) + else: + logres.append(TestRunner._run_test(test_data)) + test_data.printout = Errors.printout + test_data.printerror = Errors.printerror + + Reports.write_html_foot(test_config.html_log) + # TODO: move this elsewhere + if (len(logres)>0): + for lm in logres: + for ln in lm: + Errors.add_email_msg(ln) + + # TODO: possibly worth putting this in a sub method + if all([ test_data.overall_passed for test_data in test_data_list ]): + Errors.add_email_msg("All images passed.\n") + else: + msg = "The following images failed:\n" + for test_data in test_data_list: + if not test_data.overall_passed: + msg += "\t" + test_data.image + "\n" + Errors.add_email_msg(msg) + html = open(test_config.html_log) + Errors.add_email_attachment(html.name) + html.close() + + if test_config.email_enabled: + Emailer.send_email(test_config.mail_to, test_config.mail_server, + test_config.mail_subject, Errors.email_body, Errors.email_attachs) + + def _run_autopsy_ingest(test_data): + """Run Autopsy ingest for the image in the given TestData. + + Also generates the necessary logs for rebuilding or diff. + + Args: + test_data: the TestData to run the ingest on. + """ + if image_type(test_data.image_file) == IMGTYPE.UNKNOWN: + Errors.print_error("Error: Image type is unrecognized:") + Errors.print_error(test_data.image_file + "\n") + return + + logging.debug("--------------------") + logging.debug(test_data.image_name) + logging.debug("--------------------") + TestRunner._run_ant(test_data) + time.sleep(2) # Give everything a second to process + + try: + # Dump the database before we diff or use it for rebuild + TskDbDiff.dump_output_db(test_data.get_db_path(DBType.OUTPUT), test_data.get_db_dump_path(DBType.OUTPUT), + test_data.get_sorted_data_path(DBType.OUTPUT)) + except sqlite3.OperationalError as e: + print("Ingest did not run properly.", + "Make sure no other instances of Autopsy are open and try again.") + sys.exit() + + # merges logs into a single log for later diff / rebuild + copy_logs(test_data) + Logs.generate_log_data(test_data) + + TestRunner._handle_solr(test_data) + TestRunner._handle_exception(test_data) + + #TODO: figure out return type of _run_test (logres) + def _run_test(test_data): + """Compare the results of the output to the gold standard. + + Args: + test_data: the TestData + + Returns: + logres? + """ + TestRunner._extract_gold(test_data) + + # Look for core exceptions + # @@@ Should be moved to TestResultsDiffer, but it didn't know about logres -- need to look into that + logres = Logs.search_common_log("TskCoreException", test_data) + + TestResultsDiffer.run_diff(test_data) + test_data.overall_passed = (test_data.html_report_passed and + test_data.errors_diff_passed and test_data.db_diff_passed) + + Reports.generate_reports(test_data) + if(not test_data.overall_passed): + Errors.add_email_attachment(test_data.common_log_path) + return logres + + def _extract_gold(test_data): + """Extract gold archive file to output/gold/tmp/ + + Args: + test_data: the TestData + """ + extrctr = zipfile.ZipFile(test_data.gold_archive, 'r', compression=zipfile.ZIP_DEFLATED) + extrctr.extractall(test_data.main_config.gold) + extrctr.close + time.sleep(2) + + def _handle_solr(test_data): + """Clean up SOLR index if in keep mode (-k). + + Args: + test_data: the TestData + """ + if not test_data.main_config.args.keep: + if clear_dir(test_data.solr_index): + print_report([], "DELETE SOLR INDEX", "Solr index deleted.") + else: + print_report([], "KEEP SOLR INDEX", "Solr index has been kept.") + + def _handle_exception(test_data): + """If running in exception mode, print exceptions to log. + + Args: + test_data: the TestData + """ + if test_data.main_config.args.exception: + exceptions = search_logs(test_data.main_config.args.exception_string, test_data) + okay = ("No warnings or exceptions found containing text '" + + test_data.main_config.args.exception_string + "'.") + print_report(exceptions, "EXCEPTION", okay) + + def rebuild(test_data): + """Rebuild the gold standard with the given TestData. + + Copies the test-generated database and html report files into the gold directory. + """ + test_config = test_data.main_config + # Errors to print + errors = [] + # Delete the current gold standards + gold_dir = test_config.img_gold + clear_dir(test_config.img_gold) + tmpdir = make_path(gold_dir, test_data.image_name) + dbinpth = test_data.get_db_path(DBType.OUTPUT) + dboutpth = make_path(tmpdir, DB_FILENAME) + dataoutpth = make_path(tmpdir, test_data.image_name + "SortedData.txt") + dbdumpinpth = test_data.get_db_dump_path(DBType.OUTPUT) + dbdumpoutpth = make_path(tmpdir, test_data.image_name + "DBDump.txt") + if not os.path.exists(test_config.img_gold): + os.makedirs(test_config.img_gold) + if not os.path.exists(tmpdir): + os.makedirs(tmpdir) + try: + shutil.copy(dbinpth, dboutpth) + if file_exists(test_data.get_sorted_data_path(DBType.OUTPUT)): + shutil.copy(test_data.get_sorted_data_path(DBType.OUTPUT), dataoutpth) + shutil.copy(dbdumpinpth, dbdumpoutpth) + error_pth = make_path(tmpdir, test_data.image_name+"SortedErrors.txt") + shutil.copy(test_data.sorted_log, error_pth) + except IOError as e: + Errors.print_error(str(e)) + Errors.add_email_message("Not rebuilt properly") + print(str(e)) + print(traceback.format_exc()) + # Rebuild the HTML report + output_html_report_dir = test_data.get_html_report_path(DBType.OUTPUT) + gold_html_report_dir = make_path(tmpdir, "Report") + + try: + shutil.copytree(output_html_report_dir, gold_html_report_dir) + except OSError as e: + errors.append(e.error()) + except Exception as e: + errors.append("Error: Unknown fatal error when rebuilding the gold html report.") + errors.append(str(e) + "\n") + print(traceback.format_exc()) + oldcwd = os.getcwd() + zpdir = gold_dir + os.chdir(zpdir) + os.chdir("..") + img_gold = "tmp" + img_archive = make_path(test_data.image_name+"-archive.zip") + comprssr = zipfile.ZipFile(img_archive, 'w',compression=zipfile.ZIP_DEFLATED) + TestRunner.zipdir(img_gold, comprssr) + comprssr.close() + os.chdir(oldcwd) + del_dir(test_config.img_gold) + okay = "Sucessfully rebuilt all gold standards." + print_report(errors, "REBUILDING", okay) + + def zipdir(path, zip): + for root, dirs, files in os.walk(path): + for file in files: + zip.write(os.path.join(root, file)) + + def _run_ant(test_data): + """Construct and run the ant build command for the given TestData. + + Tests Autopsy by calling RegressionTest.java via the ant build file. + + Args: + test_data: the TestData + """ + test_config = test_data.main_config + # Set up the directories + if dir_exists(test_data.output_path): + shutil.rmtree(test_data.output_path) + os.makedirs(test_data.output_path) + test_data.ant = ["ant"] + test_data.ant.append("-v") + test_data.ant.append("-f") + # case.ant.append(case.build_path) + test_data.ant.append(os.path.join("..","..","Testing","build.xml")) + test_data.ant.append("regression-test") + test_data.ant.append("-l") + test_data.ant.append(test_data.antlog_dir) + test_data.ant.append("-Dimg_path=" + test_data.image_file) + test_data.ant.append("-Dknown_bad_path=" + test_config.known_bad_path) + test_data.ant.append("-Dkeyword_path=" + test_config.keyword_path) + test_data.ant.append("-Dnsrl_path=" + test_config.nsrl_path) + test_data.ant.append("-Dgold_path=" + test_config.gold) + test_data.ant.append("-Dout_path=" + + make_local_path(test_data.output_path)) + test_data.ant.append("-Dignore_unalloc=" + "%s" % test_config.args.unallocated) + test_data.ant.append("-Dtest.timeout=" + str(test_config.timeout)) + + Errors.print_out("Ingesting Image:\n" + test_data.image_file + "\n") + Errors.print_out("CMD: " + " ".join(test_data.ant)) + Errors.print_out("Starting test...\n") + antoutpth = make_local_path(test_data.main_config.output_dir, "antRunOutput.txt") + antout = open(antoutpth, "a") + if SYS is OS.CYGWIN: + subprocess.call(test_data.ant, stdout=subprocess.PIPE) + elif SYS is OS.WIN: + theproc = subprocess.Popen(test_data.ant, shell = True, stdout=subprocess.PIPE) + theproc.communicate() + antout.close() + + +class TestData(object): + """Container for the input and output of a single image. + + Represents data for the test of a single image, including path to the image, + database paths, etc. + + Attributes: + main_config: the global TestConfiguration + ant: a listof_String, the ant command for this TestData + image_file: a pathto_Image, the image for this TestData + image: a String, the image file's name + image_name: a String, the image file's name with a trailing (0) + output_path: pathto_Dir, the output directory for this TestData + autopsy_data_file: a pathto_File, the IMAGE_NAMEAutopsy_data.txt file + warning_log: a pathto_File, the AutopsyLogs.txt file + antlog_dir: a pathto_File, the antlog.txt file + test_dbdump: a pathto_File, the database dump, IMAGENAMEDump.txt + common_log_path: a pathto_File, the IMAGE_NAMECOMMON_LOG file + sorted_log: a pathto_File, the IMAGENAMESortedErrors.txt file + reports_dir: a pathto_Dir, the AutopsyTestCase/Reports folder + gold_data_dir: a pathto_Dir, the gold standard directory + gold_archive: a pathto_File, the gold standard archive + logs_dir: a pathto_Dir, the location where autopsy logs are stored + solr_index: a pathto_Dir, the locatino of the solr index + html_report_passed: a boolean, did the HTML report diff pass? + errors_diff_passed: a boolean, did the error diff pass? + db_diff_passed: a boolean, did the db diff pass? + overall_passed: a boolean, did the test pass? + total_test_time: a String representation of the test duration + start_date: a String representation of this TestData's start date + end_date: a String representation of the TestData's end date + total_ingest_time: a String representation of the total ingest time + artifact_count: a Nat, the number of artifacts + artifact_fail: a Nat, the number of artifact failures + heap_space: a String representation of TODO + service_times: a String representation of TODO + autopsy_version: a String, the version of autopsy that was run + ingest_messages: a Nat, the number of ingest messages + indexed_files: a Nat, the number of files indexed during the ingest + indexed_chunks: a Nat, the number of chunks indexed during the ingest + printerror: a listof_String, the error messages printed during this TestData's test + printout: a listof_String, the messages pritned during this TestData's test + """ + + def __init__(self, image, main_config): + """Init this TestData with it's image and the test configuration. + + Args: + image: the Image to be tested. + main_config: the global TestConfiguration. + """ + # Configuration Data + self.main_config = main_config + self.ant = [] + self.image_file = str(image) + # TODO: This 0 should be be refactored out, but it will require rebuilding and changing of outputs. + self.image = get_image_name(self.image_file) + self.image_name = self.image + "(0)" + # Directory structure and files + self.output_path = make_path(self.main_config.output_dir, self.image_name) + self.autopsy_data_file = make_path(self.output_path, self.image_name + "Autopsy_data.txt") + self.warning_log = make_local_path(self.output_path, "AutopsyLogs.txt") + self.antlog_dir = make_local_path(self.output_path, "antlog.txt") + self.test_dbdump = make_path(self.output_path, self.image_name + + "DBDump.txt") + self.common_log_path = make_local_path(self.output_path, self.image_name + COMMON_LOG) + self.sorted_log = make_local_path(self.output_path, self.image_name + "SortedErrors.txt") + self.reports_dir = make_path(self.output_path, AUTOPSY_TEST_CASE, "Reports") + self.gold_data_dir = make_path(self.main_config.img_gold, self.image_name) + self.gold_archive = make_path(self.main_config.gold, + self.image_name + "-archive.zip") + self.logs_dir = make_path(self.output_path, "logs") + self.solr_index = make_path(self.output_path, AUTOPSY_TEST_CASE, + "ModuleOutput", "KeywordSearch") + # Results and Info + self.html_report_passed = False + self.errors_diff_passed = False + self.db_diff_passed = False + self.overall_passed = False + # Ingest info + self.total_test_time = "" + self.start_date = "" + self.end_date = "" + self.total_ingest_time = "" + self.artifact_count = 0 + self.artifact_fail = 0 + self.heap_space = "" + self.service_times = "" + self.autopsy_version = "" + self.ingest_messages = 0 + self.indexed_files = 0 + self.indexed_chunks = 0 + # Error tracking + self.printerror = [] + self.printout = [] + + def ant_to_string(self): + string = "" + for arg in self.ant: + string += (arg + " ") + return string + + def get_db_path(self, db_type): + """Get the path to the database file that corresponds to the given DBType. + + Args: + DBType: the DBType of the path to be generated. + """ + if(db_type == DBType.GOLD): + db_path = make_path(self.gold_data_dir, DB_FILENAME) + elif(db_type == DBType.OUTPUT): + db_path = make_path(self.main_config.output_dir, self.image_name, AUTOPSY_TEST_CASE, DB_FILENAME) + else: + db_path = make_path(self.main_config.output_dir, self.image_name, AUTOPSY_TEST_CASE, BACKUP_DB_FILENAME) + return db_path + + def get_html_report_path(self, html_type): + """Get the path to the HTML Report folder that corresponds to the given DBType. + + Args: + DBType: the DBType of the path to be generated. + """ + if(html_type == DBType.GOLD): + return make_path(self.gold_data_dir, "Report") + else: + # Autopsy creates an HTML report folder in the form AutopsyTestCase DATE-TIME + # It's impossible to get the exact time the folder was created, but the folder + # we are looking for is the only one in the self.reports_dir folder + html_path = "" + for fs in os.listdir(self.reports_dir): + html_path = make_path(self.reports_dir, fs) + if os.path.isdir(html_path): + break + return make_path(html_path, os.listdir(html_path)[0]) + + def get_sorted_data_path(self, file_type): + """Get the path to the SortedData file that corresponds to the given DBType. + + Args: + file_type: the DBType of the path to be generated + """ + return self._get_path_to_file(file_type, "SortedData.txt") + + def get_sorted_errors_path(self, file_type): + """Get the path to the SortedErrors file that correspodns to the given + DBType. + + Args: + file_type: the DBType of the path to be generated + """ + return self._get_path_to_file(file_type, "SortedErrors.txt") + + def get_db_dump_path(self, file_type): + """Get the path to the DBDump file that corresponds to the given DBType. + + Args: + file_type: the DBType of the path to be generated + """ + return self._get_path_to_file(file_type, "DBDump.txt") + + def _get_path_to_file(self, file_type, file_name): + """Get the path to the specified file with the specified type. + + Args: + file_type: the DBType of the path to be generated + file_name: a String, the filename of the path to be generated + """ + full_filename = self.image_name + file_name + if(file_type == DBType.GOLD): + return make_path(self.gold_data_dir, full_filename) + else: + return make_path(self.output_path, full_filename) + + +class TestConfiguration(object): + """Container for test configuration data. + + The Master Test Configuration. Encapsulates consolidated high level input from + config XML file and command-line arguments. + + Attributes: + args: an Args, the command line arguments + output_dir: a pathto_Dir, the output directory + input_dir: a pathto_Dir, the input directory + gold: a pathto_Dir, the gold directory + img_gold: a pathto_Dir, the temp directory where gold images are unzipped to + csv: a pathto_File, the local csv file + global_csv: a pathto_File, the global csv file + html_log: a pathto_File + known_bad_path: + keyword_path: + nsrl_path: + build_path: a pathto_File, the ant build file which runs the tests + autopsy_version: + ingest_messages: a Nat, number of ingest messages + indexed_files: a Nat, the number of indexed files + indexed_chunks: a Nat, the number of indexed chunks + timer: + images: a listof_Image, the images to be tested + timeout: a Nat, the amount of time before killing the test + ant: a listof_String, the ant command to run the tests + """ + + def __init__(self, args): + """Inits TestConfiguration and loads a config file if available. + + Args: + args: an Args, the command line arguments. + """ + self.args = args + # Paths: + self.output_dir = "" + self.input_dir = make_local_path("..","input") + self.gold = make_path("..", "output", "gold") + self.img_gold = make_path(self.gold, 'tmp') + # Logs: + self.csv = "" + self.global_csv = "" + self.html_log = "" + # Ant info: + self.known_bad_path = make_path(self.input_dir, "notablehashes.txt-md5.idx") + self.keyword_path = make_path(self.input_dir, "notablekeywords.xml") + self.nsrl_path = make_path(self.input_dir, "nsrl.txt-md5.idx") + self.build_path = make_path("..", "build.xml") + # Infinite Testing info + timer = 0 + self.images = [] + # Email info + self.email_enabled = args.email_enabled + self.mail_server = "" + self.mail_to = "" + self.mail_subject = "" + # Set the timeout to something huge + # The entire tester should not timeout before this number in ms + # However it only seems to take about half this time + # And it's very buggy, so we're being careful + self.timeout = 24 * 60 * 60 * 1000 * 1000 + + if not self.args.single: + self._load_config_file(self.args.config_file) + else: + self.images.append(self.args.single_file) + self._init_logs() + #self._init_imgs() + #self._init_build_info() + + + def _load_config_file(self, config_file): + """Updates this TestConfiguration's attributes from the config file. + + Initializes this TestConfiguration by iterating through the XML config file + command-line argument. Populates self.images and optional email configuration + + Args: + config_file: ConfigFile - the configuration file to load + """ + try: + count = 0 + parsed_config = parse(config_file) + logres = [] + counts = {} + if parsed_config.getElementsByTagName("indir"): + self.input_dir = parsed_config.getElementsByTagName("indir")[0].getAttribute("value").encode().decode("utf_8") + if parsed_config.getElementsByTagName("global_csv"): + self.global_csv = parsed_config.getElementsByTagName("global_csv")[0].getAttribute("value").encode().decode("utf_8") + self.global_csv = make_local_path(self.global_csv) + if parsed_config.getElementsByTagName("golddir"): + self.gold = parsed_config.getElementsByTagName("golddir")[0].getAttribute("value").encode().decode("utf_8") + self.img_gold = make_path(self.gold, 'tmp') + + self._init_imgs(parsed_config) + self._init_build_info(parsed_config) + self._init_email_info(parsed_config) + + except IOError as e: + msg = "There was an error loading the configuration file.\n" + msg += "\t" + str(e) + Errors.add_email_msg(msg) + logging.critical(traceback.format_exc()) + print(traceback.format_exc()) + + def _init_logs(self): + """Setup output folder, logs, and reporting infrastructure.""" + if(not dir_exists(make_path("..", "output", "results"))): + os.makedirs(make_path("..", "output", "results",)) + self.output_dir = make_path("..", "output", "results", time.strftime("%Y.%m.%d-%H.%M.%S")) + os.makedirs(self.output_dir) + self.csv = make_local_path(self.output_dir, "CSV.txt") + self.html_log = make_path(self.output_dir, "AutopsyTestCase.html") + log_name = self.output_dir + "\\regression.log" + logging.basicConfig(filename=log_name, level=logging.DEBUG) + + def _init_build_info(self, parsed_config): + """Initializes paths that point to information necessary to run the AutopsyIngest.""" + build_elements = parsed_config.getElementsByTagName("build") + if build_elements: + build_element = build_elements[0] + build_path = build_element.getAttribute("value").encode().decode("utf_8") + self.build_path = build_path + + def _init_imgs(self, parsed_config): + """Initialize the list of images to run tests on.""" + for element in parsed_config.getElementsByTagName("image"): + value = element.getAttribute("value").encode().decode("utf_8") + print ("Image in Config File: " + value) + if file_exists(value): + self.images.append(value) + else: + msg = "File: " + value + " doesn't exist" + Errors.print_error(msg) + Errors.add_email_msg(msg) + image_count = len(self.images) + + # Sanity check to see if there are obvious gold images that we are not testing + gold_count = 0 + for file in os.listdir(self.gold): + if not(file == 'tmp'): + gold_count+=1 + + if (image_count > gold_count): + print("******Alert: There are more input images than gold standards, some images will not be properly tested.\n") + elif (image_count < gold_count): + print("******Alert: There are more gold standards than input images, this will not check all gold Standards.\n") + + def _init_email_info(self, parsed_config): + """Initializes email information dictionary""" + email_elements = parsed_config.getElementsByTagName("email") + if email_elements: + mail_to = email_elements[0] + self.mail_to = mail_to.getAttribute("value").encode().decode("utf_8") + mail_server_elements = parsed_config.getElementsByTagName("mail_server") + if mail_server_elements: + mail_from = mail_server_elements[0] + self.mail_server = mail_from.getAttribute("value").encode().decode("utf_8") + subject_elements = parsed_config.getElementsByTagName("subject") + if subject_elements: + subject = subject_elements[0] + self.mail_subject = subject.getAttribute("value").encode().decode("utf_8") + if self.mail_server and self.mail_to and self.args.email_enabled: + self.email_enabled = True + print("Email will be sent to ", self.mail_to) + else: + print("No email will be sent.") + + +#-------------------------------------------------# +# Functions relating to comparing outputs # +#-------------------------------------------------# +class TestResultsDiffer(object): + """Compares results for a single test.""" + + def run_diff(test_data): + """Compares results for a single test. + + Args: + test_data: the TestData to use. + databaseDiff: TskDbDiff object created based off test_data + """ + try: + output_db = test_data.get_db_path(DBType.OUTPUT) + gold_db = test_data.get_db_path(DBType.GOLD) + output_dir = test_data.output_path + gold_bb_dump = test_data.get_sorted_data_path(DBType.GOLD) + gold_dump = test_data.get_db_dump_path(DBType.GOLD) + test_data.db_diff_pass = all(TskDbDiff(output_db, gold_db, output_dir=output_dir, gold_bb_dump=gold_bb_dump, + gold_dump=gold_dump).run_diff()) + + # Compare Exceptions + # replace is a fucntion that replaces strings of digits with 'd' + # this is needed so dates and times will not cause the diff to fail + replace = lambda file: re.sub(re.compile("\d"), "d", file) + output_errors = test_data.get_sorted_errors_path(DBType.OUTPUT) + gold_errors = test_data.get_sorted_errors_path(DBType.GOLD) + passed = TestResultsDiffer._compare_text(output_errors, gold_errors, + replace) + test_data.errors_diff_passed = passed + + # Compare html output + gold_report_path = test_data.get_html_report_path(DBType.GOLD) + output_report_path = test_data.get_html_report_path(DBType.OUTPUT) + passed = TestResultsDiffer._html_report_diff(gold_report_path, + output_report_path) + test_data.html_report_passed = passed + + # Clean up tmp folder + del_dir(test_data.gold_data_dir) + + except sqlite3.OperationalError as e: + Errors.print_error("Tests failed while running the diff:\n") + Errors.print_error(str(e)) + except TskDbDiffException as e: + Errors.print_error(str(e)) + except Exception as e: + Errors.print_error("Tests failed due to an error, try rebuilding or creating gold standards.\n") + Errors.print_error(str(e) + "\n") + print(traceback.format_exc()) + + def _compare_text(output_file, gold_file, process=None): + """Compare two text files. + + Args: + output_file: a pathto_File, the output text file + gold_file: a pathto_File, the input text file + pre-process: (optional) a function of String -> String that will be + called on each input file before the diff, if specified. + """ + if(not file_exists(output_file)): + return False + output_data = codecs.open(output_file, "r", "utf_8").read() + gold_data = codecs.open(gold_file, "r", "utf_8").read() + + if process is not None: + output_data = process(output_data) + gold_data = process(gold_data) + + if (not(gold_data == output_data)): + diff_path = os.path.splitext(os.path.basename(output_file))[0] + diff_path += "-Diff.txt" + diff_file = codecs.open(diff_path, "wb", "utf_8") + dffcmdlst = ["diff", output_file, gold_file] + subprocess.call(dffcmdlst, stdout = diff_file) + Errors.add_email_attachment(diff_path) + msg = "There was a difference in " + msg += os.path.basename(output_file) + ".\n" + Errors.add_email_msg(msg) + Errors.print_error(msg) + return False + else: + return True + + def _html_report_diff(gold_report_path, output_report_path): + """Compare the output and gold html reports. + + Args: + gold_report_path: a pathto_Dir, the gold HTML report directory + output_report_path: a pathto_Dir, the output HTML report directory + + Returns: + true, if the reports match, false otherwise. + """ + try: + gold_html_files = get_files_by_ext(gold_report_path, ".html") + output_html_files = get_files_by_ext(output_report_path, ".html") + + #ensure both reports have the same number of files and are in the same order + if(len(gold_html_files) != len(output_html_files)): + msg = "The reports did not have the same number or files." + msg += "One of the reports may have been corrupted." + Errors.print_error(msg) + else: + gold_html_files.sort() + output_html_files.sort() + + total = {"Gold": 0, "New": 0} + for gold, output in zip(gold_html_files, output_html_files): + count = TestResultsDiffer._compare_report_files(gold, output) + total["Gold"] += count[0] + total["New"] += count[1] + + okay = "The test report matches the gold report." + errors=["Gold report had " + str(total["Gold"]) +" errors", "New report had " + str(total["New"]) + " errors."] + print_report(errors, "REPORT COMPARISON", okay) + + if total["Gold"] == total["New"]: + return True + else: + Errors.print_error("The reports did not match each other.\n " + errors[0] +" and the " + errors[1]) + return False + except OSError as e: + e.print_error() + return False + except Exception as e: + Errors.print_error("Error: Unknown fatal error comparing reports.") + Errors.print_error(str(e) + "\n") + logging.critical(traceback.format_exc()) + return False + + def _compare_report_files(a_path, b_path): + """Compares the two specified report html files. + + Args: + a_path: a pathto_File, the first html report file + b_path: a pathto_File, the second html report file + + Returns: + a tuple of (Nat, Nat), which represent the length of each + unordered list in the html report files, or (0, 0) if the + lenghts are the same. + """ + a_file = open(a_path) + b_file = open(b_path) + a = a_file.read() + b = b_file.read() + a = a[a.find("
        "):] + b = b[b.find("
          "):] + + a_list = TestResultsDiffer._split(a, 50) + b_list = TestResultsDiffer._split(b, 50) + if not len(a_list) == len(b_list): + ex = (len(a_list), len(b_list)) + return ex + else: + return (0, 0) + + # Split a string into an array of string of the given size + def _split(input, size): + return [input[start:start+size] for start in range(0, len(input), size)] + + +class Reports(object): + def generate_reports(test_data): + """Generate the reports for a single test + + Args: + test_data: the TestData + """ + Reports._generate_html(test_data) + if test_data.main_config.global_csv: + Reports._generate_csv(test_data.main_config.global_csv, test_data) + else: + Reports._generate_csv(test_data.main_config.csv, test_data) + + def _generate_html(test_data): + """Generate the HTML log file.""" + # If the file doesn't exist yet, this is the first test_config to run for + # this test, so we need to make the start of the html log + html_log = test_data.main_config.html_log + if not file_exists(html_log): + Reports.write_html_head() + with open(html_log, "a") as html: + # The image title + title = "

          " + test_data.image_name + " \ + tested on " + socket.gethostname() + "

          \ +

          \ + Errors and Warnings |\ + Information |\ + General Output |\ + Logs\ +

          " + # The script errors found + if not test_data.overall_passed: + ids = 'errors1' + else: + ids = 'errors' + errors = "
          \ +

          Errors and Warnings

          \ +
          " + # For each error we have logged in the test_config + for error in test_data.printerror: + # Replace < and > to avoid any html display errors + errors += "

          " + error.replace("<", "<").replace(">", ">") + "

          " + # If there is a \n, we probably want a
          in the html + if "\n" in error: + errors += "
          " + errors += "
          " + + # Links to the logs + logs = "
          \ +

          Logs

          \ +
          " + logs_path = test_data.logs_dir + for file in os.listdir(logs_path): + logs += "

          " + file + "

          " + logs += "
          " + + # All the testing information + info = "
          \ +

          Information

          \ +
          \ + " + # The individual elements + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" + info += "" +# info += "" +# info += "" +# info += "" +# info += "" +# info += "" +# info += "" + info += "
          Image Path:" + test_data.image_file + "
          Image Name:" + test_data.image_name + "
          test_config Output Directory:" + test_data.main_config.output_dir + "
          Autopsy Version:" + test_data.autopsy_version + "
          Heap Space:" + test_data.heap_space + "
          Test Start Date:" + test_data.start_date + "
          Test End Date:" + test_data.end_date + "
          Total Test Time:" + test_data.total_test_time + "
          Total Ingest Time:" + test_data.total_ingest_time + "
          Exceptions Count:" + str(len(get_exceptions(test_data))) + "
          Autopsy OutOfMemoryExceptions:" + str(len(search_logs("OutOfMemoryException", test_data))) + "
          Autopsy OutOfMemoryErrors:" + str(len(search_logs("OutOfMemoryError", test_data))) + "
          Tika OutOfMemoryErrors/Exceptions:" + str(Reports._get_num_memory_errors("tika", test_data)) + "
          Solr OutOfMemoryErrors/Exceptions:" + str(Reports._get_num_memory_errors("solr", test_data)) + "
          TskCoreExceptions:" + str(len(search_log_set("autopsy", "TskCoreException", test_data))) + "
          TskDataExceptions:" + str(len(search_log_set("autopsy", "TskDataException", test_data))) + "
          Ingest Messages Count:" + str(test_data.ingest_messages) + "
          Indexed Files Count:" + str(test_data.indexed_files) + "
          Indexed File Chunks Count:" + str(test_data.indexed_chunks) + "
          Out Of Disk Space:\ +

          (will skew other test results)

          		" + str(len(search_log_set("autopsy", "Stopping ingest due to low disk space on disk", test_data))) + "
          TSK Objects Count:" + str(test_data.db_diff_results.output_objs) + "
          Artifacts Count:" + str(test_data.db_diff_results.output_artifacts)+ "
          Attributes Count:" + str(test_data.db_diff_results.output_attrs) + "
          \ +
          " + # For all the general print statements in the test_config + output = "
          \ +

          General Output

          \ +
          " + # For each printout in the test_config's list + for out in test_data.printout: + output += "

          " + out + "

          " + # If there was a \n it probably means we want a
          in the html + if "\n" in out: + output += "
          " + output += "
          " + + html.write(title) + html.write(errors) + html.write(info) + html.write(logs) + html.write(output) + + def write_html_head(html_log): + """Write the top of the HTML log file. + + Args: + html_log: a pathto_File, the global HTML log + """ + with open(str(html_log), "a") as html: + head = "\ + \ + AutopsyTesttest_config Output\ + \ + \ + " + html.write(head) + + def write_html_foot(html_log): + """Write the bottom of the HTML log file. + + Args: + html_log: a pathto_File, the global HTML log + """ + with open(html_log, "a") as html: + head = "" + html.write(head) + + def html_add_images(html_log, full_image_names): + """Add all the image names to the HTML log. + + Args: + full_image_names: a listof_String, each representing an image name + html_log: a pathto_File, the global HTML log + """ + # If the file doesn't exist yet, this is the first test_config to run for + # this test, so we need to make the start of the html log + if not file_exists(html_log): + Reports.write_html_head(html_log) + with open(html_log, "a") as html: + links = [] + for full_name in full_image_names: + name = get_image_name(full_name) + links.append("" + name + "") + html.write("

          " + (" | ".join(links)) + "

          ") + + def _generate_csv(csv_path, test_data): + """Generate the CSV log file""" + # If the CSV file hasn't already been generated, this is the + # first run, and we need to add the column names + if not file_exists(csv_path): + Reports.csv_header(csv_path) + # Now add on the fields to a new row + with open(csv_path, "a") as csv: + # Variables that need to be written + vars = [] + vars.append( test_data.image_file ) + vars.append( test_data.image_name ) + vars.append( test_data.main_config.output_dir ) + vars.append( socket.gethostname() ) + vars.append( test_data.autopsy_version ) + vars.append( test_data.heap_space ) + vars.append( test_data.start_date ) + vars.append( test_data.end_date ) + vars.append( test_data.total_test_time ) + vars.append( test_data.total_ingest_time ) + vars.append( test_data.service_times ) + vars.append( str(len(get_exceptions(test_data))) ) + vars.append( str(Reports._get_num_memory_errors("autopsy", test_data)) ) + vars.append( str(Reports._get_num_memory_errors("tika", test_data)) ) + vars.append( str(Reports._get_num_memory_errors("solr", test_data)) ) + vars.append( str(len(search_log_set("autopsy", "TskCoreException", test_data))) ) + vars.append( str(len(search_log_set("autopsy", "TskDataException", test_data))) ) + vars.append( str(test_data.ingest_messages) ) + vars.append( str(test_data.indexed_files) ) + vars.append( str(test_data.indexed_chunks) ) + vars.append( str(len(search_log_set("autopsy", "Stopping ingest due to low disk space on disk", test_data))) ) +# vars.append( str(test_data.db_diff_results.output_objs) ) +# vars.append( str(test_data.db_diff_results.output_artifacts) ) +# vars.append( str(test_data.db_diff_results.output_objs) ) + vars.append( make_local_path("gold", test_data.image_name, DB_FILENAME) ) +# vars.append( test_data.db_diff_results.get_artifact_comparison() ) +# vars.append( test_data.db_diff_results.get_attribute_comparison() ) + vars.append( make_local_path("gold", test_data.image_name, "standard.html") ) + vars.append( str(test_data.html_report_passed) ) + vars.append( test_data.ant_to_string() ) + # Join it together with a ", " + output = "|".join(vars) + output += "\n" + # Write to the log! + csv.write(output) + + def csv_header(csv_path): + """Generate the CSV column names.""" + with open(csv_path, "w") as csv: + titles = [] + titles.append("Image Path") + titles.append("Image Name") + titles.append("Output test_config Directory") + titles.append("Host Name") + titles.append("Autopsy Version") + titles.append("Heap Space Setting") + titles.append("Test Start Date") + titles.append("Test End Date") + titles.append("Total Test Time") + titles.append("Total Ingest Time") + titles.append("Service Times") + titles.append("Autopsy Exceptions") + titles.append("Autopsy OutOfMemoryErrors/Exceptions") + titles.append("Tika OutOfMemoryErrors/Exceptions") + titles.append("Solr OutOfMemoryErrors/Exceptions") + titles.append("TskCoreExceptions") + titles.append("TskDataExceptions") + titles.append("Ingest Messages Count") + titles.append("Indexed Files Count") + titles.append("Indexed File Chunks Count") + titles.append("Out Of Disk Space") +# titles.append("Tsk Objects Count") +# titles.append("Artifacts Count") +# titles.append("Attributes Count") + titles.append("Gold Database Name") +# titles.append("Artifacts Comparison") +# titles.append("Attributes Comparison") + titles.append("Gold Report Name") + titles.append("Report Comparison") + titles.append("Ant Command Line") + output = "|".join(titles) + output += "\n" + csv.write(output) + + def _get_num_memory_errors(type, test_data): + """Get the number of OutOfMemory errors and Exceptions. + + Args: + type: a String representing the type of log to check. + test_data: the TestData to examine. + """ + return (len(search_log_set(type, "OutOfMemoryError", test_data)) + + len(search_log_set(type, "OutOfMemoryException", test_data))) + +class Logs(object): + + def generate_log_data(test_data): + """Find and handle relevent data from the Autopsy logs. + + Args: + test_data: the TestData whose logs to examine + """ + Logs._generate_common_log(test_data) + try: + Logs._fill_ingest_data(test_data) + except Exception as e: + Errors.print_error("Error: Unknown fatal error when filling test_config data.") + Errors.print_error(str(e) + "\n") + logging.critical(traceback.format_exc()) + # If running in verbose mode (-v) + if test_data.main_config.args.verbose: + errors = Logs._report_all_errors() + okay = "No warnings or errors in any log files." + print_report(errors, "VERBOSE", okay) + + def _generate_common_log(test_data): + """Generate the common log, the log of all exceptions and warnings from + each log file generated by Autopsy. + + Args: + test_data: the TestData to generate a log for + """ + try: + logs_path = test_data.logs_dir + common_log = codecs.open(test_data.common_log_path, "w", "utf_8") + warning_log = codecs.open(test_data.warning_log, "w", "utf_8") + common_log.write("--------------------------------------------------\n") + common_log.write(test_data.image_name + "\n") + common_log.write("--------------------------------------------------\n") + rep_path = make_local_path(test_data.main_config.output_dir) + rep_path = rep_path.replace("\\\\", "\\") + for file in os.listdir(logs_path): + log = codecs.open(make_path(logs_path, file), "r", "utf_8") + for line in log: + line = line.replace(rep_path, "test_data") + if line.startswith("Exception"): + common_log.write(file +": " + line) + elif line.startswith("Error"): + common_log.write(file +": " + line) + elif line.startswith("SEVERE"): + common_log.write(file +":" + line) + else: + warning_log.write(file +": " + line) + log.close() + common_log.write("\n") + common_log.close() + print(test_data.sorted_log) + srtcmdlst = ["sort", test_data.common_log_path, "-o", test_data.sorted_log] + subprocess.call(srtcmdlst) + except (OSError, IOError) as e: + Errors.print_error("Error: Unable to generate the common log.") + Errors.print_error(str(e) + "\n") + Errors.print_error(traceback.format_exc()) + logging.critical(traceback.format_exc()) + + def _fill_ingest_data(test_data): + """Fill the TestDatas variables that require the log files. + + Args: + test_data: the TestData to modify + """ + try: + # Open autopsy.log.0 + log_path = make_path(test_data.logs_dir, "autopsy.log.0") + log = open(log_path) + + # Set the TestData start time based off the first line of autopsy.log.0 + # *** If logging time format ever changes this will break *** + test_data.start_date = log.readline().split(" org.")[0] + + # Set the test_data ending time based off the "create" time (when the file was copied) + test_data.end_date = time.ctime(os.path.getmtime(log_path)) + except IOError as e: + Errors.print_error("Error: Unable to open autopsy.log.0.") + Errors.print_error(str(e) + "\n") + logging.warning(traceback.format_exc()) + # Start date must look like: "Jul 16, 2012 12:57:53 PM" + # End date must look like: "Mon Jul 16 13:02:42 2012" + # *** If logging time format ever changes this will break *** + start = datetime.datetime.strptime(test_data.start_date, "%b %d, %Y %I:%M:%S %p") + end = datetime.datetime.strptime(test_data.end_date, "%a %b %d %H:%M:%S %Y") + test_data.total_test_time = str(end - start) + + try: + # Set Autopsy version, heap space, ingest time, and service times + + version_line = search_logs("INFO: Application name: Autopsy, version:", test_data)[0] + test_data.autopsy_version = get_word_at(version_line, 5).rstrip(",") + + test_data.heap_space = search_logs("Heap memory usage:", test_data)[0].rstrip().split(": ")[1] + + ingest_line = search_logs("Ingest (including enqueue)", test_data)[0] + test_data.total_ingest_time = get_word_at(ingest_line, 6).rstrip() + + message_line = search_log_set("autopsy", "Ingest messages count:", test_data)[0] + test_data.ingest_messages = int(message_line.rstrip().split(": ")[2]) + + files_line = search_log_set("autopsy", "Indexed files count:", test_data)[0] + test_data.indexed_files = int(files_line.rstrip().split(": ")[2]) + + chunks_line = search_log_set("autopsy", "Indexed file chunks count:", test_data)[0] + test_data.indexed_chunks = int(chunks_line.rstrip().split(": ")[2]) + except (OSError, IOError) as e: + Errors.print_error("Error: Unable to find the required information to fill test_config data.") + Errors.print_error(str(e) + "\n") + logging.critical(traceback.format_exc()) + print(traceback.format_exc()) + try: + service_lines = search_log("autopsy.log.0", "to process()", test_data) + service_list = [] + for line in service_lines: + words = line.split(" ") + # Kind of forcing our way into getting this data + # If this format changes, the tester will break + i = words.index("secs.") + times = words[i-4] + " " + times += words[i-3] + " " + times += words[i-2] + " " + times += words[i-1] + " " + times += words[i] + service_list.append(times) + test_data.service_times = "; ".join(service_list) + except (OSError, IOError) as e: + Errors.print_error("Error: Unknown fatal error when finding service times.") + Errors.print_error(str(e) + "\n") + logging.critical(traceback.format_exc()) + + def _report_all_errors(): + """Generate a list of all the errors found in the common log. + + Returns: + a listof_String, the errors found in the common log + """ + try: + return get_warnings() + get_exceptions() + except (OSError, IOError) as e: + Errors.print_error("Error: Unknown fatal error when reporting all errors.") + Errors.print_error(str(e) + "\n") + logging.warning(traceback.format_exc()) + + def search_common_log(string, test_data): + """Search the common log for any instances of a given string. + + Args: + string: the String to search for. + test_data: the TestData that holds the log to search. + + Returns: + a listof_String, all the lines that the string is found on + """ + results = [] + log = codecs.open(test_data.common_log_path, "r", "utf_8") + for line in log: + if string in line: + results.append(line) + log.close() + return results + + +def print_report(errors, name, okay): + """Print a report with the specified information. + + Args: + errors: a listof_String, the errors to report. + name: a String, the name of the report. + okay: the String to print when there are no errors. + """ + if errors: + Errors.print_error("--------< " + name + " >----------") + for error in errors: + Errors.print_error(str(error)) + Errors.print_error("--------< / " + name + " >--------\n") + else: + Errors.print_out("-----------------------------------------------------------------") + Errors.print_out("< " + name + " - " + okay + " />") + Errors.print_out("-----------------------------------------------------------------\n") + + +def get_exceptions(test_data): + """Get a list of the exceptions in the autopsy logs. + + Args: + test_data: the TestData to use to find the exceptions. + Returns: + a listof_String, the exceptions found in the logs. + """ + exceptions = [] + logs_path = test_data.logs_dir + results = [] + for file in os.listdir(logs_path): + if "autopsy.log" in file: + log = codecs.open(make_path(logs_path, file), "r", "utf_8") + ex = re.compile("\SException") + er = re.compile("\SError") + for line in log: + if ex.search(line) or er.search(line): + exceptions.append(line) + log.close() + return exceptions + +def get_warnings(test_data): + """Get a list of the warnings listed in the common log. + + Args: + test_data: the TestData to use to find the warnings + + Returns: + listof_String, the warnings found. + """ + warnings = [] + common_log = codecs.open(test_data.warning_log, "r", "utf_8") + for line in common_log: + if "warning" in line.lower(): + warnings.append(line) + common_log.close() + return warnings + +def copy_logs(test_data): + """Copy the Autopsy generated logs to output directory. + + Args: + test_data: the TestData whose logs will be copied + """ + try: + log_dir = os.path.join("..", "..", "Testing","build","test","qa-functional","work","userdir0","var","log") + shutil.copytree(log_dir, test_data.logs_dir) + except OSError as e: + printerror(test_data,"Error: Failed to copy the logs.") + printerror(test_data,str(e) + "\n") + logging.warning(traceback.format_exc()) + +def setDay(): + global Day + Day = int(strftime("%d", localtime())) + +def getLastDay(): + return Day + +def getDay(): + return int(strftime("%d", localtime())) + +def newDay(): + return getLastDay() != getDay() + +#------------------------------------------------------------# +# Exception classes to manage "acceptable" thrown exceptions # +# versus unexpected and fatal exceptions # +#------------------------------------------------------------# + +class FileNotFoundException(Exception): + """ + If a file cannot be found by one of the helper functions, + they will throw a FileNotFoundException unless the purpose + is to return False. + """ + def __init__(self, file): + self.file = file + self.strerror = "FileNotFoundException: " + file + + def print_error(self): + Errors.print_error("Error: File could not be found at:") + Errors.print_error(self.file + "\n") + + def error(self): + error = "Error: File could not be found at:\n" + self.file + "\n" + return error + +class DirNotFoundException(Exception): + """ + If a directory cannot be found by a helper function, + it will throw this exception + """ + def __init__(self, dir): + self.dir = dir + self.strerror = "DirNotFoundException: " + dir + + def print_error(self): + Errors.print_error("Error: Directory could not be found at:") + Errors.print_error(self.dir + "\n") + + def error(self): + error = "Error: Directory could not be found at:\n" + self.dir + "\n" + return error + + +class Errors: + """A class used to manage error reporting. + + Attributes: + printout: a listof_String, the non-error messages that were printed + printerror: a listof_String, the error messages that were printed + email_body: a String, the body of the report email + email_msg_prefix: a String, the prefix for lines added to the email + email_attchs: a listof_pathto_File, the files to be attached to the + report email + """ + printout = [] + printerror = [] + email_body = "" + email_msg_prefix = "Configuration" + email_attachs = [] + + def set_testing_phase(image_name): + """Change the email message prefix to be the given testing phase. + + Args: + image_name: a String, representing the current image being tested + """ + Errors.email_msg_prefix = image_name + + def print_out(msg): + """Print out an informational message. + + Args: + msg: a String, the message to be printed + """ + print(msg) + Errors.printout.append(msg) + + def print_error(msg): + """Print out an error message. + + Args: + msg: a String, the error message to be printed. + """ + print(msg) + Errors.printerror.append(msg) + + def clear_print_logs(): + """Reset the image-specific attributes of the Errors class.""" + Errors.printout = [] + Errors.printerror = [] + + def add_email_msg(msg): + """Add the given message to the body of the report email. + + Args: + msg: a String, the message to be added to the email + """ + Errors.email_body += Errors.email_msg_prefix + ":" + msg + + def add_email_attachment(path): + """Add the given file to be an attachment for the report email + + Args: + file: a pathto_File, the file to add + """ + Errors.email_attachs.append(path) + + +class DiffResults(object): + """Container for the results of the database diff tests. + + Stores artifact, object, and attribute counts and comparisons generated by + TskDbDiff. + + Attributes: + gold_attrs: a Nat, the number of gold attributes + output_attrs: a Nat, the number of output attributes + gold_objs: a Nat, the number of gold objects + output_objs: a Nat, the number of output objects + artifact_comp: a listof_String, describing the differences + attribute_comp: a listof_String, describing the differences + passed: a boolean, did the diff pass? + """ + def __init__(self, tsk_diff): + """Inits a DiffResults + + Args: + tsk_diff: a TskDBDiff + """ + self.gold_attrs = tsk_diff.gold_attributes + self.output_attrs = tsk_diff.autopsy_attributes + self.gold_objs = tsk_diff.gold_objects + self.output_objs = tsk_diff.autopsy_objects + self.artifact_comp = tsk_diff.artifact_comparison + self.attribute_comp = tsk_diff.attribute_comparison + self.gold_artifacts = len(tsk_diff.gold_artifacts) + self.output_artifacts = len(tsk_diff.autopsy_artifacts) + self.passed = tsk_diff.passed + + def get_artifact_comparison(self): + if not self.artifact_comp: + return "All counts matched" + else: + return "; ".join(self.artifact_comp) + + def get_attribute_comparison(self): + if not self.attribute_comp: + return "All counts matched" + list = [] + for error in self.attribute_comp: + list.append(error) + return ";".join(list) + + +#-------------------------------------------------------------# +# Parses argv and stores booleans to match command line input # +#-------------------------------------------------------------# +class Args(object): + """A container for command line options and arguments. + + Attributes: + single: a boolean indicating whether to run in single file mode + single_file: an Image to run the test on + rebuild: a boolean indicating whether to run in rebuild mode + list: a boolean indicating a config file was specified + unallocated: a boolean indicating unallocated space should be ignored + ignore: a boolean indicating the input directory should be ingnored + keep: a boolean indicating whether to keep the SOLR index + verbose: a boolean indicating whether verbose output should be printed + exeception: a boolean indicating whether errors containing exception + exception_string should be printed + exception_sring: a String representing and exception name + fr: a boolean indicating whether gold standard images will be downloaded + """ + def __init__(self): + self.single = False + self.single_file = "" + self.rebuild = False + self.list = False + self.config_file = "" + self.unallocated = False + self.ignore = False + self.keep = False + self.verbose = False + self.exception = False + self.exception_string = "" + self.fr = False + self.email_enabled = False + + def parse(self): + """Get the command line arguments and parse them.""" + nxtproc = [] + nxtproc.append("python3") + nxtproc.append(sys.argv.pop(0)) + while sys.argv: + arg = sys.argv.pop(0) + nxtproc.append(arg) + if(arg == "-f"): + #try: @@@ Commented out until a more specific except statement is added + arg = sys.argv.pop(0) + print("Running on a single file:") + print(path_fix(arg) + "\n") + self.single = True + self.single_file = path_fix(arg) + #except: + # print("Error: No single file given.\n") + # return False + elif(arg == "-r" or arg == "--rebuild"): + print("Running in rebuild mode.\n") + self.rebuild = True + elif(arg == "-l" or arg == "--list"): + try: + arg = sys.argv.pop(0) + nxtproc.append(arg) + print("Running from configuration file:") + print(arg + "\n") + self.list = True + self.config_file = arg + except: + print("Error: No configuration file given.\n") + return False + elif(arg == "-u" or arg == "--unallocated"): + print("Ignoring unallocated space.\n") + self.unallocated = True + elif(arg == "-k" or arg == "--keep"): + print("Keeping the Solr index.\n") + self.keep = True + elif(arg == "-v" or arg == "--verbose"): + print("Running in verbose mode:") + print("Printing all thrown exceptions.\n") + self.verbose = True + elif(arg == "-e" or arg == "--exception"): + try: + arg = sys.argv.pop(0) + nxtproc.append(arg) + print("Running in exception mode: ") + print("Printing all exceptions with the string '" + arg + "'\n") + self.exception = True + self.exception_string = arg + except: + print("Error: No exception string given.") + elif arg == "-h" or arg == "--help": + print(usage()) + return False + elif arg == "-fr" or arg == "--forcerun": + print("Not downloading new images") + self.fr = True + elif arg == "-e" or arg == "-email": + self.email_enabled = True + else: + print(usage()) + return False + # Return the args were sucessfully parsed + return self._sanity_check() + + def _sanity_check(self): + """Check to make sure there are no conflicting arguments and the + specified files exist. + + Returns: + False if there are conflicting arguments or a specified file does + not exist, True otherwise + """ + if self.single and self.list: + print("Cannot run both from config file and on a single file.") + return False + if self.list: + if not file_exists(self.config_file): + print("Configuration file does not exist at:", + self.config_file) + return False + elif self.single: + if not file_exists(self.single_file): + msg = "Image file does not exist at: " + self.single_file + return False + if (not self.single) and (not self.ignore) and (not self.list): + self.config_file = "config.xml" + if not file_exists(self.config_file): + msg = "Configuration file does not exist at: " + self.config_file + return False + + return True + +#### +# Helper Functions +#### +def search_logs(string, test_data): + """Search through all the known log files for a given string. + + Args: + string: the String to search for. + test_data: the TestData that holds the logs to search. + + Returns: + a listof_String, the lines that contained the given String. + """ + logs_path = test_data.logs_dir + results = [] + for file in os.listdir(logs_path): + log = codecs.open(make_path(logs_path, file), "r", "utf_8") + for line in log: + if string in line: + results.append(line) + log.close() + return results + +def search_log(log, string, test_data): + """Search the given log for any instances of a given string. + + Args: + log: a pathto_File, the log to search in + string: the String to search for. + test_data: the TestData that holds the log to search. + + Returns: + a listof_String, all the lines that the string is found on + """ + logs_path = make_path(test_data.logs_dir, log) + try: + results = [] + log = codecs.open(logs_path, "r", "utf_8") + for line in log: + if string in line: + results.append(line) + log.close() + if results: + return results + except: + raise FileNotFoundException(logs_path) + +# Search through all the the logs of the given type +# Types include autopsy, tika, and solr +def search_log_set(type, string, test_data): + """Search through all logs to the given type for the given string. + + Args: + type: the type of log to search in. + string: the String to search for. + test_data: the TestData containing the logs to search. + + Returns: + a listof_String, the lines on which the String was found. + """ + logs_path = test_data.logs_dir + results = [] + for file in os.listdir(logs_path): + if type in file: + log = codecs.open(make_path(logs_path, file), "r", "utf_8") + for line in log: + if string in line: + results.append(line) + log.close() + return results + + +def clear_dir(dir): + """Clears all files from a directory and remakes it. + + Args: + dir: a pathto_Dir, the directory to clear + """ + try: + if dir_exists(dir): + shutil.rmtree(dir) + os.makedirs(dir) + return True; + except OSError as e: + printerror(test_data,"Error: Cannot clear the given directory:") + printerror(test_data,dir + "\n") + print(str(e)) + return False; + +def del_dir(dir): + """Delete the given directory. + + Args: + dir: a pathto_Dir, the directory to delete + """ + try: + if dir_exists(dir): + shutil.rmtree(dir) + return True; + except: + printerror(test_data,"Error: Cannot delete the given directory:") + printerror(test_data,dir + "\n") + return False; + +def get_file_in_dir(dir, ext): + """Returns the first file in the given directory with the given extension. + + Args: + dir: a pathto_Dir, the directory to search + ext: a String, the extension to search for + + Returns: + pathto_File, the file that was found + """ + try: + for file in os.listdir(dir): + if file.endswith(ext): + return make_path(dir, file) + # If nothing has been found, raise an exception + raise FileNotFoundException(dir) + except: + raise DirNotFoundException(dir) + +def find_file_in_dir(dir, name, ext): + """Find the file with the given name in the given directory. + + Args: + dir: a pathto_Dir, the directory to search + name: a String, the basename of the file to search for + ext: a String, the extension of the file to search for + """ + try: + for file in os.listdir(dir): + if file.startswith(name): + if file.endswith(ext): + return make_path(dir, file) + raise FileNotFoundException(dir) + except: + raise DirNotFoundException(dir) + + +class OS: + LINUX, MAC, WIN, CYGWIN = range(4) + + +if __name__ == "__main__": + global SYS + if _platform == "linux" or _platform == "linux2": + SYS = OS.LINUX + elif _platform == "darwin": + SYS = OS.MAC + elif _platform == "win32": + SYS = OS.WIN + elif _platform == "cygwin": + SYS = OS.CYGWIN + + if SYS is OS.WIN or SYS is OS.CYGWIN: + main() + else: + print("We only support Windows and Cygwin at this time.") diff --git a/test/script/srcupdater.py b/test/script/srcupdater.py index 99a393d9eb..c8c7d5410b 100644 --- a/test/script/srcupdater.py +++ b/test/script/srcupdater.py @@ -1,187 +1,187 @@ -import codecs -import datetime -import logging -import os -import re -import shutil -import socket -import sqlite3 -import subprocess -import sys -from sys import platform as _platform -import time -import traceback -import xml -from xml.dom.minidom import parse, parseString -import Emailer -from regression_utils import * - -def compile(errore, attachli, parsedin): - global redo - global tryredo - global failedbool - global errorem - errorem = errore - global attachl - attachl = attachli - global passed - global parsed - parsed = parsedin - passed = True - tryredo = False - redo = True - while(redo): - passed = True - if(passed): - gitPull("sleuthkit") - if(passed): - vsBuild() - if(passed): - gitPull("autopsy") - if(passed): - antBuild("datamodel", False) - if(passed): - antBuild("autopsy", True) - if(passed): - redo = False - else: - print("Compile Failed") - time.sleep(3600) - attachl = [] - errorem = "The test standard didn't match the gold standard.\n" - failedbool = False - if(tryredo): - errorem = "" - errorem += "Rebuilt properly.\n" - Emailer.send_email(parsed, errorem, attachl, True) - attachl = [] - passed = True - -#Pulls from git -def gitPull(TskOrAutopsy): - global SYS - global errorem - global attachl - ccwd = "" - gppth = make_local_path("..", "GitPullOutput" + TskOrAutopsy + ".txt") - attachl.append(gppth) - gpout = open(gppth, 'a') - toPull = "https://www.github.com/sleuthkit/" + TskOrAutopsy - call = ["git", "pull", toPull] - if TskOrAutopsy == "sleuthkit": - ccwd = os.path.join("..", "..", "..", "sleuthkit") - else: - ccwd = os.path.join("..", "..") - subprocess.call(call, stdout=sys.stdout, cwd=ccwd) - gpout.close() - - -#Builds TSK as a win32 applicatiion -def vsBuild(): - global redo - global tryredo - global passed - global parsed - #Please ensure that the current working directory is $autopsy/testing/script - oldpath = os.getcwd() - os.chdir(os.path.join("..", "..", "..","sleuthkit", "win32")) - vs = [] - vs.append("/cygdrive/c/windows/microsoft.NET/framework/v4.0.30319/MSBuild.exe") - vs.append(os.path.join("Tsk-win.sln")) - vs.append("/p:configuration=release") - vs.append("/p:platform=win32") - vs.append("/t:clean") - vs.append("/t:rebuild") - print(vs) - VSpth = make_local_path("..", "VSOutput.txt") - VSout = open(VSpth, 'a') - subprocess.call(vs, stdout=VSout) - VSout.close() - os.chdir(oldpath) - chk = os.path.join("..", "..", "..","sleuthkit", "win32", "Release", "libtsk_jni.dll") - try: - open(chk) - except IOError as e: - global errorem - global attachl - if(not tryredo): - errorem += "LIBTSK C++ failed to build.\n" - attachl.append(VSpth) - send_email(parsed, errorem, attachl, False) - tryredo = True - passed = False - redo = True - - - -#Builds Autopsy or the Datamodel -def antBuild(which, Build): - global redo - global passed - global tryredo - global parsed - directory = os.path.join("..", "..") - ant = [] - if which == "datamodel": - directory = os.path.join("..", "..", "..", "sleuthkit", "bindings", "java") - ant.append("ant") - ant.append("-f") - ant.append(directory) - ant.append("clean") - if(Build): - ant.append("build") - else: - ant.append("dist") - antpth = make_local_path("..", "ant" + which + "Output.txt") - antout = open(antpth, 'a') - succd = subprocess.call(ant, stdout=antout) - antout.close() - global errorem - global attachl - if which == "datamodel": - chk = os.path.join("..", "..", "..","sleuthkit", "bindings", "java", "dist", "TSK_DataModel.jar") - try: - open(chk) - except IOError as e: - if(not tryredo): - errorem += "DataModel Java build failed.\n" - attachl.append(antpth) - Emailer.send_email(parsed, errorem, attachl, False) - passed = False - tryredo = True - elif (succd != 0 and (not tryredo)): - errorem += "Autopsy build failed.\n" - attachl.append(antpth) - Emailer.send_email(parsed, errorem, attachl, False) - tryredo = True - elif (succd != 0): - passed = False - - -def main(): - errore = "" - attachli = [] - config_file = "" - arg = sys.argv.pop(0) - arg = sys.argv.pop(0) - config_file = arg - parsedin = parse(config_file) - compile(errore, attachli, parsedin) - -class OS: - LINUX, MAC, WIN, CYGWIN = range(4) -if __name__ == "__main__": - global SYS - if _platform == "linux" or _platform == "linux2": - SYS = OS.LINUX - elif _platform == "darwin": - SYS = OS.MAC - elif _platform == "win32": - SYS = OS.WIN - elif _platform == "cygwin": - SYS = OS.CYGWIN - - if SYS is OS.WIN or SYS is OS.CYGWIN: - main() - else: - print("We only support Windows and Cygwin at this time.") +import codecs +import datetime +import logging +import os +import re +import shutil +import socket +import sqlite3 +import subprocess +import sys +from sys import platform as _platform +import time +import traceback +import xml +from xml.dom.minidom import parse, parseString +import Emailer +from regression_utils import * + +def compile(errore, attachli, parsedin): + global redo + global tryredo + global failedbool + global errorem + errorem = errore + global attachl + attachl = attachli + global passed + global parsed + parsed = parsedin + passed = True + tryredo = False + redo = True + while(redo): + passed = True + if(passed): + gitPull("sleuthkit") + if(passed): + vsBuild() + if(passed): + gitPull("autopsy") + if(passed): + antBuild("datamodel", False) + if(passed): + antBuild("autopsy", True) + if(passed): + redo = False + else: + print("Compile Failed") + time.sleep(3600) + attachl = [] + errorem = "The test standard didn't match the gold standard.\n" + failedbool = False + if(tryredo): + errorem = "" + errorem += "Rebuilt properly.\n" + Emailer.send_email(parsed, errorem, attachl, True) + attachl = [] + passed = True + +#Pulls from git +def gitPull(TskOrAutopsy): + global SYS + global errorem + global attachl + ccwd = "" + gppth = make_local_path("..", "GitPullOutput" + TskOrAutopsy + ".txt") + attachl.append(gppth) + gpout = open(gppth, 'a') + toPull = "https://www.github.com/sleuthkit/" + TskOrAutopsy + call = ["git", "pull", toPull] + if TskOrAutopsy == "sleuthkit": + ccwd = os.path.join("..", "..", "..", "sleuthkit") + else: + ccwd = os.path.join("..", "..") + subprocess.call(call, stdout=sys.stdout, cwd=ccwd) + gpout.close() + + +#Builds TSK as a win32 applicatiion +def vsBuild(): + global redo + global tryredo + global passed + global parsed + #Please ensure that the current working directory is $autopsy/testing/script + oldpath = os.getcwd() + os.chdir(os.path.join("..", "..", "..","sleuthkit", "win32")) + vs = [] + vs.append("/cygdrive/c/windows/microsoft.NET/framework/v4.0.30319/MSBuild.exe") + vs.append(os.path.join("Tsk-win.sln")) + vs.append("/p:configuration=release") + vs.append("/p:platform=win32") + vs.append("/t:clean") + vs.append("/t:rebuild") + print(vs) + VSpth = make_local_path("..", "VSOutput.txt") + VSout = open(VSpth, 'a') + subprocess.call(vs, stdout=VSout) + VSout.close() + os.chdir(oldpath) + chk = os.path.join("..", "..", "..","sleuthkit", "win32", "Release", "libtsk_jni.dll") + try: + open(chk) + except IOError as e: + global errorem + global attachl + if(not tryredo): + errorem += "LIBTSK C++ failed to build.\n" + attachl.append(VSpth) + send_email(parsed, errorem, attachl, False) + tryredo = True + passed = False + redo = True + + + +#Builds Autopsy or the Datamodel +def antBuild(which, Build): + global redo + global passed + global tryredo + global parsed + directory = os.path.join("..", "..") + ant = [] + if which == "datamodel": + directory = os.path.join("..", "..", "..", "sleuthkit", "bindings", "java") + ant.append("ant") + ant.append("-f") + ant.append(directory) + ant.append("clean") + if(Build): + ant.append("build") + else: + ant.append("dist") + antpth = make_local_path("..", "ant" + which + "Output.txt") + antout = open(antpth, 'a') + succd = subprocess.call(ant, stdout=antout) + antout.close() + global errorem + global attachl + if which == "datamodel": + chk = os.path.join("..", "..", "..","sleuthkit", "bindings", "java", "dist", "TSK_DataModel.jar") + try: + open(chk) + except IOError as e: + if(not tryredo): + errorem += "DataModel Java build failed.\n" + attachl.append(antpth) + Emailer.send_email(parsed, errorem, attachl, False) + passed = False + tryredo = True + elif (succd != 0 and (not tryredo)): + errorem += "Autopsy build failed.\n" + attachl.append(antpth) + Emailer.send_email(parsed, errorem, attachl, False) + tryredo = True + elif (succd != 0): + passed = False + + +def main(): + errore = "" + attachli = [] + config_file = "" + arg = sys.argv.pop(0) + arg = sys.argv.pop(0) + config_file = arg + parsedin = parse(config_file) + compile(errore, attachli, parsedin) + +class OS: + LINUX, MAC, WIN, CYGWIN = range(4) +if __name__ == "__main__": + global SYS + if _platform == "linux" or _platform == "linux2": + SYS = OS.LINUX + elif _platform == "darwin": + SYS = OS.MAC + elif _platform == "win32": + SYS = OS.WIN + elif _platform == "cygwin": + SYS = OS.CYGWIN + + if SYS is OS.WIN or SYS is OS.CYGWIN: + main() + else: + print("We only support Windows and Cygwin at this time.") diff --git a/thunderbirdparser/manifest.mf b/thunderbirdparser/manifest.mf index c16a2f4c01..fc34c0e90a 100644 --- a/thunderbirdparser/manifest.mf +++ b/thunderbirdparser/manifest.mf @@ -1,7 +1,7 @@ -Manifest-Version: 1.0 -AutoUpdate-Show-In-Client: true -OpenIDE-Module: org.sleuthkit.autopsy.thunderbirdparser/3 -OpenIDE-Module-Implementation-Version: 9 -OpenIDE-Module-Layer: org/sleuthkit/autopsy/thunderbirdparser/layer.xml -OpenIDE-Module-Localizing-Bundle: org/sleuthkit/autopsy/thunderbirdparser/Bundle.properties - +Manifest-Version: 1.0 +AutoUpdate-Show-In-Client: true +OpenIDE-Module: org.sleuthkit.autopsy.thunderbirdparser/3 +OpenIDE-Module-Implementation-Version: 9 +OpenIDE-Module-Layer: org/sleuthkit/autopsy/thunderbirdparser/layer.xml +OpenIDE-Module-Localizing-Bundle: org/sleuthkit/autopsy/thunderbirdparser/Bundle.properties + diff --git a/thunderbirdparser/nbproject/project.properties b/thunderbirdparser/nbproject/project.properties index 6a243df466..0735c621fa 100644 --- a/thunderbirdparser/nbproject/project.properties +++ b/thunderbirdparser/nbproject/project.properties @@ -1,6 +1,6 @@ -javac.source=1.7 -javac.compilerargs=-Xlint -Xlint:-serial -license.file=../LICENSE-2.0.txt -nbm.homepage=http://www.sleuthkit.org/autopsy/ -nbm.needs.restart=true -spec.version.base=1.2 +javac.source=1.7 +javac.compilerargs=-Xlint -Xlint:-serial +license.file=../LICENSE-2.0.txt +nbm.homepage=http://www.sleuthkit.org/autopsy/ +nbm.needs.restart=true +spec.version.base=1.2 diff --git a/update_versions.py b/update_versions.py index 2883021c9f..fa228d0cca 100644 --- a/update_versions.py +++ b/update_versions.py @@ -1,939 +1,939 @@ -# -# Autopsy Forensic Browser -# -# Copyright 2012-2013 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. - - -####################### -# This script exists to help us determine update the library -# versions appropriately. See this page for version details. -# -# http://wiki.sleuthkit.org/index.php?title=Autopsy_3_Module_Versions -# -# The basic idea is that this script uses javadoc/jdiff to -# compare the current state of the source code to the last -# tag and identifies if APIs were removed, added, etc. -# -# When run from the Autopsy build script, this script will: -# - Clone Autopsy and checkout to the previous release tag -# as found in the NEWS.txt file -# - Auto-discover all modules and packages -# - Run jdiff, comparing the current and previous modules -# - Use jdiff's output to determine if each module -# a) has no changes -# b) has backwards compatible changes -# c) has backwards incompatible changes -# - Based off it's compatibility, updates each module's -# a) Major version -# b) Specification version -# c) Implementation version -# - Updates the dependencies on each module depending on the -# updated version numbers -# -# Optionally, when run from the command line, one can provide the -# desired tag to compare the current version to, the directory for -# the current version of Autopsy, and whether to automatically -# update the version numbers and dependencies. -# ------------------------------------------------------------ - -import errno -import os -import shutil -import stat -import subprocess -import sys -import traceback -from os import remove, close -from shutil import move -from tempfile import mkstemp -from xml.dom.minidom import parse, parseString - -# Jdiff return codes. Described in more detail further on -NO_CHANGES = 100 -COMPATIBLE = 101 -NON_COMPATIBLE = 102 -ERROR = 1 - -# An Autopsy module object -class Module: - # Initialize it with a name, return code, and version numbers - def __init__(self, name=None, ret=None, versions=None): - self.name = name - self.ret = ret - self.versions = versions - # As a string, the module should be it's name - def __str__(self): - return self.name - def __repr__(self): - return self.name - # When compared to another module, the two are equal if the names are the same - def __cmp__(self, other): - if isinstance(other, Module): - if self.name == other.name: - return 0 - elif self.name < other.name: - return -1 - else: - return 1 - return 1 - def __eq__(self, other): - if isinstance(other, Module): - if self.name == other.name: - return True - return False - def set_name(self, name): - self.name = name - def set_ret(self, ret): - self.ret = ret - def set_versions(self, versions): - self.versions = versions - def spec(self): - return self.versions[0] - def impl(self): - return self.versions[1] - def release(self): - return self.versions[2] - -# Representation of the Specification version number -class Spec: - # Initialize specification number, where num is a string like x.y - def __init__(self, num): - self.third = None - spec_nums = num.split(".") - if len(spec_nums) == 3: - final = spec_nums[2] - self.third = int(final) - - l, r = spec_nums[0], spec_nums[1] - - self.left = int(l) - self.right = int(r) - - def __str__(self): - return self.get() - def __cmp__(self, other): - if isinstance(other, Spec): - if self.left == other.left: - if self.right == other.right: - return 0 - if self.right < other.right: - return -1 - return 1 - if self.left < other.left: - return -1 - return 1 - elif isinstance(other, str): - l, r = other.split(".") - if self.left == int(l): - if self.right == int(r): - return 0 - if self.right < int(r): - return -1 - return 1 - if self.left < int(l): - return -1 - return 1 - return -1 - - def overflow(self): - return str(self.left + 1) + ".0" - def increment(self): - return str(self.left) + "." + str(self.right + 1) - def get(self): - spec_str = str(self.left) + "." + str(self.right) - if self.third is not None: - spec_str += "." + str(self.final) - return spec_str - def set(self, num): - if isinstance(num, str): - l, r = num.split(".") - self.left = int(l) - self.right = int(r) - elif isinstance(num, Spec): - self.left = num.left - self.right = num.right - return self - -# ================================ # -# Core Functions # -# ================================ # - -# Given a list of modules and the names for each version, compare -# the generated jdiff XML for each module and output the jdiff -# JavaDocs. -# -# modules: the list of all modules both versions have in common -# apiname_tag: the api name of the previous version, most likely the tag -# apiname_cur: the api name of the current version, most likely "Current" -# -# returns the exit code from the modified jdiff.jar -# return code 1 = error in jdiff -# return code 100 = no changes -# return code 101 = compatible changes -# return code 102 = incompatible changes -def compare_xml(module, apiname_tag, apiname_cur): - global docdir - make_dir(docdir) - null_file = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/lib/Null.java")) - jdiff = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/jdiff.jar")) - oldapi = fix_path("build/jdiff-xml/" + apiname_tag + "-" + module.name) - newapi = fix_path("build/jdiff-xml/" + apiname_cur + "-" + module.name) - docs = fix_path(docdir + "/" + module.name) - # Comments are strange. They look for a file with additional user comments in a - # directory like docs/user_comments_for_xyz. The problem being that xyz is the - # path to the new/old api. So xyz turns into multiple directories for us. - # i.e. user_comments_for_build/jdiff-xml/[tag name]-[module name]_to_build/jdiff-xml - comments = fix_path(docs + "/user_comments_for_build") - jdiff_com = fix_path(comments + "/jdiff-xml") - tag_comments = fix_path(jdiff_com + "/" + apiname_tag + "-" + module.name + "_to_build") - jdiff_tag_com = fix_path(tag_comments + "/jdiff-xml") - - if not os.path.exists(jdiff): - print("JDIFF doesn't exist.") - - make_dir(docs) - make_dir(comments) - make_dir(jdiff_com) - make_dir(tag_comments) - make_dir(jdiff_tag_com) - make_dir("jdiff-logs") - log = open("jdiff-logs/COMPARE-" + module.name + ".log", "w") - cmd = ["javadoc", - "-doclet", "jdiff.JDiff", - "-docletpath", jdiff, - "-d", docs, - "-oldapi", oldapi, - "-newapi", newapi, - "-script", - null_file] - jdiff = subprocess.Popen(cmd, stdout=log, stderr=log) - jdiff.wait() - log.close() - code = jdiff.returncode - print("Compared XML for " + module.name) - if code == NO_CHANGES: - print(" No API changes") - elif code == COMPATIBLE: - print(" API Changes are backwards compatible") - elif code == NON_COMPATIBLE: - print(" API Changes are not backwards compatible") - else: - print(" *Error in XML, most likely an empty module") - sys.stdout.flush() - return code - -# Generate the jdiff xml for the given module -# path: path to the autopsy source -# module: Module object -# name: api name for jdiff -def gen_xml(path, modules, name): - for module in modules: - # If its the regression test, the source is in the "test" dir - if module.name == "Testing": - src = os.path.join(path, module.name, "test", "qa-functional", "src") - else: - src = os.path.join(path, module.name, "src") - # xerces = os.path.abspath("./lib/xerces.jar") - xml_out = fix_path(os.path.abspath("./build/jdiff-xml/" + name + "-" + module.name)) - jdiff = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/jdiff.jar")) - make_dir("build/jdiff-xml") - make_dir("jdiff-logs") - log = open("jdiff-logs/GEN_XML-" + name + "-" + module.name + ".log", "w") - cmd = ["javadoc", - "-doclet", "jdiff.JDiff", - "-docletpath", jdiff, # ;" + xerces, <-- previous problems required this - "-apiname", xml_out, # leaving it in just in case it's needed once again - "-sourcepath", fix_path(src)] - cmd = cmd + get_packages(src) - jdiff = subprocess.Popen(cmd, stdout=log, stderr=log) - jdiff.wait() - log.close() - print("Generated XML for " + name + " " + module.name) - sys.stdout.flush() - -# Find all the modules in the given path -def find_modules(path): - modules = [] - # Step into each folder in the given path and - # see if it has manifest.mf - if so, it's a module - for dir in os.listdir(path): - directory = os.path.join(path, dir) - if os.path.isdir(directory): - for file in os.listdir(directory): - if file == "manifest.mf": - modules.append(Module(dir, None, None)) - return modules - -# Detects the differences between the source and tag modules -def module_diff(source_modules, tag_modules): - added_modules = [x for x in source_modules if x not in tag_modules] - removed_modules = [x for x in tag_modules if x not in source_modules] - similar_modules = [x for x in source_modules if x in tag_modules] - - added_modules = (added_modules if added_modules else []) - removed_modules = (removed_modules if removed_modules else []) - similar_modules = (similar_modules if similar_modules else []) - return similar_modules, added_modules, removed_modules - -# Reads the previous tag from NEWS.txt -def get_tag(sourcepath): - news = open(sourcepath + "/NEWS.txt", "r") - second_instance = False - for line in news: - if "----------------" in line: - if second_instance: - ver = line.split("VERSION ")[1] - ver = ver.split(" -")[0] - return ("autopsy-" + ver).strip() - else: - second_instance = True - continue - news.close() - - -# ========================================== # -# Dependency Functions # -# ========================================== # - -# Write a new XML file, copying all the lines from projectxml -# and replacing the specification version for the code-name-base base -# with the supplied specification version spec -def set_dep_spec(projectxml, base, spec): - print(" Updating Specification version..") - orig = open(projectxml, "r") - f, abs_path = mkstemp() - new_file = open(abs_path, "w") - found_base = False - spacing = " " - sopen = "" - sclose = "\n" - for line in orig: - if base in line: - found_base = True - if found_base and sopen in line: - update = spacing + sopen + str(spec) + sclose - new_file.write(update) - else: - new_file.write(line) - new_file.close() - close(f) - orig.close() - remove(projectxml) - move(abs_path, projectxml) - -# Write a new XML file, copying all the lines from projectxml -# and replacing the release version for the code-name-base base -# with the supplied release version -def set_dep_release(projectxml, base, release): - print(" Updating Release version..") - orig = open(projectxml, "r") - f, abs_path = mkstemp() - new_file = open(abs_path, "w") - found_base = False - spacing = " " - ropen = "" - rclose = "\n" - for line in orig: - if base in line: - found_base = True - if found_base and ropen in line: - update = spacing + ropen + str(release) + rclose - new_file.write(update) - else: - new_file.write(line) - new_file.close() - close(f) - orig.close() - remove(projectxml) - move(abs_path, projectxml) - -# Return the dependency versions in the XML dependency node -def get_dep_versions(dep): - run_dependency = dep.getElementsByTagName("run-dependency")[0] - release_version = run_dependency.getElementsByTagName("release-version") - if release_version: - release_version = getTagText(release_version[0].childNodes) - specification_version = run_dependency.getElementsByTagName("specification-version") - if specification_version: - specification_version = getTagText(specification_version[0].childNodes) - return int(release_version), Spec(specification_version) - -# Given a code-name-base, see if it corresponds with any of our modules -def get_module_from_base(modules, code_name_base): - for module in modules: - if "org.sleuthkit.autopsy." + module.name.lower() == code_name_base: - return module - return None # If it didn't match one of our modules - -# Check the text between two XML tags -def getTagText(nodelist): - for node in nodelist: - if node.nodeType == node.TEXT_NODE: - return node.data - -# Check the projectxml for a dependency on any module in modules -def check_for_dependencies(projectxml, modules): - dom = parse(projectxml) - dep_list = dom.getElementsByTagName("dependency") - for dep in dep_list: - code_name_base = dep.getElementsByTagName("code-name-base")[0] - code_name_base = getTagText(code_name_base.childNodes) - module = get_module_from_base(modules, code_name_base) - if module: - print(" Found dependency on " + module.name) - release, spec = get_dep_versions(dep) - if release != module.release() and module.release() is not None: - set_dep_release(projectxml, code_name_base, module.release()) - else: print(" Release version is correct") - if spec != module.spec() and module.spec() is not None: - set_dep_spec(projectxml, code_name_base, module.spec()) - else: print(" Specification version is correct") - -# Given the module and the source directory, return -# the paths to the manifest and project properties files -def get_dependency_file(module, source): - projectxml = os.path.join(source, module.name, "nbproject", "project.xml") - if os.path.isfile(projectxml): - return projectxml - -# Verify/Update the dependencies for each module, basing the dependency -# version number off the versions in each module -def update_dependencies(modules, source): - for module in modules: - print("Checking the dependencies for " + module.name + "...") - projectxml = get_dependency_file(module, source) - if projectxml == None: - print(" Error finding project xml file") - else: - other = [x for x in modules] - check_for_dependencies(projectxml, other) - sys.stdout.flush() - -# ======================================== # -# Versioning Functions # -# ======================================== # - -# Return the specification version in the given project.properties/manifest.mf file -def get_specification(project, manifest): - try: - # Try to find it in the project file - # it will be there if impl version is set to append automatically - f = open(project, 'r') - for line in f: - if "spec.version.base" in line: - return Spec(line.split("=")[1].strip()) - f.close() - # If not found there, try the manifest file - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module-Specification-Version:" in line: - return Spec(line.split(": ")[1].strip()) - except Exception as e: - print("Error parsing Specification version for") - print(project) - print(e) - -# Set the specification version in the given project properties file -# but if it can't be found there, set it in the manifest file -def set_specification(project, manifest, num): - try: - # First try the project file - f = open(project, 'r') - for line in f: - if "spec.version.base" in line: - f.close() - replace(project, line, "spec.version.base=" + str(num) + "\n") - return - f.close() - # If it's not there, try the manifest file - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module-Specification-Version:" in line: - f.close() - replace(manifest, line, "OpenIDE-Module-Specification-Version: " + str(num) + "\n") - return - # Otherwise we're out of luck - print(" Error finding the Specification version to update") - print(" " + manifest) - f.close() - except: - print(" Error incrementing Specification version for") - print(" " + project) - -# Return the implementation version in the given manifest.mf file -def get_implementation(manifest): - try: - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module-Implementation-Version" in line: - return int(line.split(": ")[1].strip()) - f.close() - except: - print("Error parsing Implementation version for") - print(manifest) - -# Set the implementation version in the given manifest file -def set_implementation(manifest, num): - try: - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module-Implementation-Version" in line: - f.close() - replace(manifest, line, "OpenIDE-Module-Implementation-Version: " + str(num) + "\n") - return - # If it isn't there, add it - f.close() - write_implementation(manifest, num) - except: - print(" Error incrementing Implementation version for") - print(" " + manifest) - -# Rewrite the manifest file to include the implementation version -def write_implementation(manifest, num): - f = open(manifest, "r") - contents = f.read() - contents = contents[:-2] + "OpenIDE-Module-Implementation-Version: " + str(num) + "\n\n" - f.close() - f = open(manifest, "w") - f.write(contents) - f.close() - -# Return the release version in the given manifest.mf file -def get_release(manifest): - try: - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module:" in line: - return int(line.split("/")[1].strip()) - f.close() - except: - #print("Error parsing Release version for") - #print(manifest) - return 0 - -# Set the release version in the given manifest file -def set_release(manifest, num): - try: - f = open(manifest, 'r') - for line in f: - if "OpenIDE-Module:" in line: - f.close() - index = line.index('/') - len(line) + 1 - newline = line[:index] + str(num) - replace(manifest, line, newline + "\n") - return - print(" Error finding the release version to update") - print(" " + manifest) - f.close() - except: - print(" Error incrementing release version for") - print(" " + manifest) - -# Given the module and the source directory, return -# the paths to the manifest and project properties files -def get_version_files(module, source): - manifest = os.path.join(source, module.name, "manifest.mf") - project = os.path.join(source, module.name, "nbproject", "project.properties") - if os.path.isfile(manifest) and os.path.isfile(project): - return manifest, project - -# Returns a the current version numbers for the module in source -def get_versions(module, source): - manifest, project = get_version_files(module, source) - if manifest == None or project == None: - print(" Error finding manifeset and project properties files") - return - spec = get_specification(project, manifest) - impl = get_implementation(manifest) - release = get_release(manifest) - return [spec, impl, release] - -# Update the version numbers for every module in modules -def update_versions(modules, source): - for module in modules: - versions = module.versions - manifest, project = get_version_files(module, source) - print("Updating " + module.name + "...") - if manifest == None or project == None: - print(" Error finding manifeset and project properties files") - return - if module.ret == COMPATIBLE: - versions = [versions[0].set(versions[0].increment()), versions[1] + 1, versions[2]] - set_specification(project, manifest, versions[0]) - set_implementation(manifest, versions[1]) - module.set_versions(versions) - elif module.ret == NON_COMPATIBLE: - versions = [versions[0].set(versions[0].overflow()), versions[1] + 1, versions[2] + 1] - set_specification(project, manifest, versions[0]) - set_implementation(manifest, versions[1]) - set_release(manifest, versions[2]) - module.set_versions(versions) - elif module.ret == NO_CHANGES: - versions = [versions[0], versions[1] + 1, versions[2]] - set_implementation(manifest, versions[1]) - module.set_versions(versions) - elif module.ret == None: - versions = [Spec("1.0"), 1, 1] - set_specification(project, manifest, versions[0]) - set_implementation(manifest, versions[1]) - set_release(manifest, versions[2]) - module.set_versions(versions) - sys.stdout.flush() - -# Given a list of the added modules, remove the modules -# which have the correct 'new module default' version number -def remove_correct_added(modules): - correct = [x for x in modules] - for module in modules: - if module.spec() == "1.0" or module.spec() == "0.0": - if module.impl() == 1: - if module.release() == 1 or module.release() == 0: - correct.remove(module) - return correct - -# ==================================== # -# Helper Functions # -# ==================================== # - -# Replace pattern with subst in given file -def replace(file, pattern, subst): - #Create temp file - fh, abs_path = mkstemp() - new_file = open(abs_path,'w') - old_file = open(file) - for line in old_file: - new_file.write(line.replace(pattern, subst)) - #close temp file - new_file.close() - close(fh) - old_file.close() - #Remove original file - remove(file) - #Move new file - move(abs_path, file) - -# Given a list of modules print the version numbers that need changing -def print_version_updates(modules): - f = open("gen_version.txt", "a") - for module in modules: - versions = module.versions - if module.ret == COMPATIBLE: - output = (module.name + ":\n") - output += ("\tSpecification:\t" + str(versions[0]) + "\t->\t" + str(versions[0].increment()) + "\n") - output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") - output += ("\tRelease:\tNo Change.\n") - output += ("\n") - print(output) - sys.stdout.flush() - f.write(output) - elif module.ret == NON_COMPATIBLE: - output = (module.name + ":\n") - output += ("\tSpecification:\t" + str(versions[0]) + "\t->\t" + str(versions[0].overflow()) + "\n") - output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") - output += ("\tRelease:\t" + str(versions[2]) + "\t->\t" + str(versions[2] + 1) + "\n") - output += ("\n") - print(output) - sys.stdout.flush() - f.write(output) - elif module.ret == ERROR: - output = (module.name + ":\n") - output += ("\t*Unable to detect necessary changes\n") - output += ("\tSpecification:\t" + str(versions[0]) + "\n") - output += ("\tImplementation:\t" + str(versions[1]) + "\n") - output += ("\tRelease:\t\t" + str(versions[2]) + "\n") - output += ("\n") - print(output) - f.write(output) - sys.stdout.flush() - elif module.ret == NO_CHANGES: - output = (module.name + ":\n") - if versions[1] is None: - output += ("\tImplementation: None\n") - else: - output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") - output += ("\n") - print(output) - sys.stdout.flush() - f.write(output) - elif module.ret is None: - output = ("Added " + module.name + ":\n") - if module.spec() != "1.0" and module.spec() != "0.0": - output += ("\tSpecification:\t" + str(module.spec()) + "\t->\t" + "1.0\n") - output += ("\n") - if module.impl() != 1: - output += ("\tImplementation:\t" + str(module.impl()) + "\t->\t" + "1\n") - output += ("\n") - if module.release() != 1 and module.release() != 0: - output += ("Release:\t\t" + str(module.release()) + "\t->\t" + "1\n") - output += ("\n") - print(output) - sys.stdout.flush() - f.write(output) - sys.stdout.flush() - f.close() - -# Changes cygwin paths to Windows -def fix_path(path): - if "cygdrive" in path: - new_path = path[11:] - return "C:/" + new_path - else: - return path - -# Print a 'title' -def printt(title): - print("\n" + title) - lines = "" - for letter in title: - lines += "-" - print(lines) - sys.stdout.flush() - -# Get a list of package names in the given path -# The path is expected to be of the form {base}/module/src -# -# NOTE: We currently only check for packages of the form -# org.sleuthkit.autopsy.x -# If we add other namespaces for commercial modules we will -# have to add a check here -def get_packages(path): - packages = [] - package_path = os.path.join(path, "org", "sleuthkit", "autopsy") - for folder in os.listdir(package_path): - package_string = "org.sleuthkit.autopsy." - packages.append(package_string + folder) - return packages - -# Create the given directory, if it doesn't already exist -def make_dir(dir): - try: - if not os.path.isdir(dir): - os.mkdir(dir) - if os.path.isdir(dir): - return True - return False - except: - print("Exception thrown when creating directory") - return False - -# Delete the given directory, and make sure it is deleted -def del_dir(dir): - try: - if os.path.isdir(dir): - shutil.rmtree(dir, ignore_errors=False, onerror=handleRemoveReadonly) - if os.path.isdir(dir): - return False - else: - return True - return True - except: - print("Exception thrown when deleting directory") - traceback.print_exc() - return False - -# Handle any permisson errors thrown by shutil.rmtree -def handleRemoveReadonly(func, path, exc): - excvalue = exc[1] - if func in (os.rmdir, os.remove) and excvalue.errno == errno.EACCES: - os.chmod(path, stat.S_IRWXU| stat.S_IRWXG| stat.S_IRWXO) # 0777 - func(path) - else: - raise - -# Run git clone and git checkout for the tag -def do_git(tag, tag_dir): - try: - printt("Cloning Autopsy tag " + tag + " into dir " + tag_dir + " (this could take a while)...") - subprocess.call(["git", "clone", "https://github.com/sleuthkit/autopsy.git", tag_dir], - stdout=subprocess.PIPE) - printt("Checking out tag " + tag + "...") - subprocess.call(["git", "checkout", tag], - stdout=subprocess.PIPE, - cwd=tag_dir) - return True - except Exception as ex: - print("Error cloning and checking out Autopsy: ", sys.exc_info()[0]) - print(str(ex)) - print("The terminal you are using most likely does not recognize git commands.") - return False - -# Get the flags from argv -def args(): - try: - sys.argv.pop(0) - while sys.argv: - arg = sys.argv.pop(0) - if arg == "-h" or arg == "--help": - return 1 - elif arg == "-t" or arg == "--tag": - global tag - tag = sys.argv.pop(0) - elif arg == "-s" or arg == "--source": - global source - source = sys.argv.pop(0) - elif arg == "-d" or arg == "--dir": - global docdir - docdir = sys.argv.pop(0) - elif arg == "-a" or arg == "--auto": - global dry - dry = False - else: - raise Exception() - except: - pass - -# Print script run info -def printinfo(): - global tag - global source - global docdir - global dry - printt("Release script information:") - if source is None: - source = fix_path(os.path.abspath(".")) - print("Using source directory:\n " + source) - if tag is None: - tag = get_tag(source) - print("Checking out to tag:\n " + tag) - if docdir is None: - docdir = fix_path(os.path.abspath("./jdiff-javadocs")) - print("Generating jdiff JavaDocs in:\n " + docdir) - if dry is True: - print("Dry run: will not auto-update version numbers") - sys.stdout.flush() - -# Print the script's usage/help -def usage(): - return \ - """ - USAGE: - Compares the API of the current Autopsy source code with a previous - tagged version. By default, it will detect the previous tag from - the NEWS file and will not update the versions in the source code. - - OPTIONAL FLAGS: - -t --tag Specify a previous tag to compare to. - Otherwise the NEWS file will be used. - - -d --dir The output directory for the jdiff JavaDocs. If no - directory is given, the default is jdiff-javadocs/{module}. - - -s --source The directory containing Autopsy's source code. - - -a --auto Automatically update version numbers (not dry). - - -h --help Prints this usage. - """ - -# ==================================== # -# Main Functionality # -# ==================================== # - -# Where the magic happens -def main(): - global tag; global source; global docdir; global dry - tag = None; source = None; docdir = None; dry = True - - ret = args() - if ret: - print(usage()) - return 0 - printinfo() - - # ----------------------------------------------- - # 1) Clone Autopsy, checkout to given tag/commit - # 2) Get the modules in the clone and the source - # 3) Generate the xml comparison - # ----------------------------------------------- - if not del_dir("./build/" + tag): - print("\n\n=========================================") - print(" Failed to delete previous Autopsy clone.") - print(" Unable to continue...") - print("=========================================") - return 1 - tag_dir = os.path.abspath("./build/" + tag) - if not do_git(tag, tag_dir): - return 1 - sys.stdout.flush() - - tag_modules = find_modules(tag_dir) - source_modules = find_modules(source) - - printt("Generating jdiff XML reports...") - apiname_tag = tag - apiname_cur = "current" - gen_xml(tag_dir, tag_modules, apiname_tag) - gen_xml(source, source_modules, apiname_cur) - - printt("Deleting cloned Autopsy directory...") - print("Clone successfully deleted" if del_dir(tag_dir) else "Failed to delete clone") - sys.stdout.flush() - - # ----------------------------------------------------- - # 1) Seperate modules into added, similar, and removed - # 2) Compare XML for each module - # ----------------------------------------------------- - printt("Comparing modules found...") - similar_modules, added_modules, removed_modules = module_diff(source_modules, tag_modules) - if added_modules or removed_modules: - for m in added_modules: - print("+ Added " + m.name) - sys.stdout.flush() - for m in removed_modules: - print("- Removed " + m.name) - sys.stdout.flush() - else: - print("No added or removed modules") - sys.stdout.flush() - - printt("Comparing jdiff outputs...") - for module in similar_modules: - module.set_ret(compare_xml(module, apiname_tag, apiname_cur)) - print("Refer to the jdiff-javadocs folder for more details") - - # ------------------------------------------------------------ - # 1) Do versioning - # 2) Auto-update version numbers in files and the_modules list - # 3) Auto-update dependencies - # ------------------------------------------------------------ - printt("Auto-detecting version numbers and changes...") - for module in added_modules: - module.set_versions(get_versions(module, source)) - for module in similar_modules: - module.set_versions(get_versions(module, source)) - - added_modules = remove_correct_added(added_modules) - the_modules = similar_modules + added_modules - print_version_updates(the_modules) - - if not dry: - printt("Auto-updating version numbers...") - update_versions(the_modules, source) - print("All auto-updates complete") - - printt("Detecting and auto-updating dependencies...") - update_dependencies(the_modules, source) - - printt("Deleting jdiff XML...") - xml_dir = os.path.abspath("./build/jdiff-xml") - print("XML successfully deleted" if del_dir(xml_dir) else "Failed to delete XML") - - print("\n--- Script completed successfully ---") - return 0 - -# Start off the script -if __name__ == "__main__": - sys.exit(main()) +# +# Autopsy Forensic Browser +# +# Copyright 2012-2013 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. + + +####################### +# This script exists to help us determine update the library +# versions appropriately. See this page for version details. +# +# http://wiki.sleuthkit.org/index.php?title=Autopsy_3_Module_Versions +# +# The basic idea is that this script uses javadoc/jdiff to +# compare the current state of the source code to the last +# tag and identifies if APIs were removed, added, etc. +# +# When run from the Autopsy build script, this script will: +# - Clone Autopsy and checkout to the previous release tag +# as found in the NEWS.txt file +# - Auto-discover all modules and packages +# - Run jdiff, comparing the current and previous modules +# - Use jdiff's output to determine if each module +# a) has no changes +# b) has backwards compatible changes +# c) has backwards incompatible changes +# - Based off it's compatibility, updates each module's +# a) Major version +# b) Specification version +# c) Implementation version +# - Updates the dependencies on each module depending on the +# updated version numbers +# +# Optionally, when run from the command line, one can provide the +# desired tag to compare the current version to, the directory for +# the current version of Autopsy, and whether to automatically +# update the version numbers and dependencies. +# ------------------------------------------------------------ + +import errno +import os +import shutil +import stat +import subprocess +import sys +import traceback +from os import remove, close +from shutil import move +from tempfile import mkstemp +from xml.dom.minidom import parse, parseString + +# Jdiff return codes. Described in more detail further on +NO_CHANGES = 100 +COMPATIBLE = 101 +NON_COMPATIBLE = 102 +ERROR = 1 + +# An Autopsy module object +class Module: + # Initialize it with a name, return code, and version numbers + def __init__(self, name=None, ret=None, versions=None): + self.name = name + self.ret = ret + self.versions = versions + # As a string, the module should be it's name + def __str__(self): + return self.name + def __repr__(self): + return self.name + # When compared to another module, the two are equal if the names are the same + def __cmp__(self, other): + if isinstance(other, Module): + if self.name == other.name: + return 0 + elif self.name < other.name: + return -1 + else: + return 1 + return 1 + def __eq__(self, other): + if isinstance(other, Module): + if self.name == other.name: + return True + return False + def set_name(self, name): + self.name = name + def set_ret(self, ret): + self.ret = ret + def set_versions(self, versions): + self.versions = versions + def spec(self): + return self.versions[0] + def impl(self): + return self.versions[1] + def release(self): + return self.versions[2] + +# Representation of the Specification version number +class Spec: + # Initialize specification number, where num is a string like x.y + def __init__(self, num): + self.third = None + spec_nums = num.split(".") + if len(spec_nums) == 3: + final = spec_nums[2] + self.third = int(final) + + l, r = spec_nums[0], spec_nums[1] + + self.left = int(l) + self.right = int(r) + + def __str__(self): + return self.get() + def __cmp__(self, other): + if isinstance(other, Spec): + if self.left == other.left: + if self.right == other.right: + return 0 + if self.right < other.right: + return -1 + return 1 + if self.left < other.left: + return -1 + return 1 + elif isinstance(other, str): + l, r = other.split(".") + if self.left == int(l): + if self.right == int(r): + return 0 + if self.right < int(r): + return -1 + return 1 + if self.left < int(l): + return -1 + return 1 + return -1 + + def overflow(self): + return str(self.left + 1) + ".0" + def increment(self): + return str(self.left) + "." + str(self.right + 1) + def get(self): + spec_str = str(self.left) + "." + str(self.right) + if self.third is not None: + spec_str += "." + str(self.final) + return spec_str + def set(self, num): + if isinstance(num, str): + l, r = num.split(".") + self.left = int(l) + self.right = int(r) + elif isinstance(num, Spec): + self.left = num.left + self.right = num.right + return self + +# ================================ # +# Core Functions # +# ================================ # + +# Given a list of modules and the names for each version, compare +# the generated jdiff XML for each module and output the jdiff +# JavaDocs. +# +# modules: the list of all modules both versions have in common +# apiname_tag: the api name of the previous version, most likely the tag +# apiname_cur: the api name of the current version, most likely "Current" +# +# returns the exit code from the modified jdiff.jar +# return code 1 = error in jdiff +# return code 100 = no changes +# return code 101 = compatible changes +# return code 102 = incompatible changes +def compare_xml(module, apiname_tag, apiname_cur): + global docdir + make_dir(docdir) + null_file = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/lib/Null.java")) + jdiff = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/jdiff.jar")) + oldapi = fix_path("build/jdiff-xml/" + apiname_tag + "-" + module.name) + newapi = fix_path("build/jdiff-xml/" + apiname_cur + "-" + module.name) + docs = fix_path(docdir + "/" + module.name) + # Comments are strange. They look for a file with additional user comments in a + # directory like docs/user_comments_for_xyz. The problem being that xyz is the + # path to the new/old api. So xyz turns into multiple directories for us. + # i.e. user_comments_for_build/jdiff-xml/[tag name]-[module name]_to_build/jdiff-xml + comments = fix_path(docs + "/user_comments_for_build") + jdiff_com = fix_path(comments + "/jdiff-xml") + tag_comments = fix_path(jdiff_com + "/" + apiname_tag + "-" + module.name + "_to_build") + jdiff_tag_com = fix_path(tag_comments + "/jdiff-xml") + + if not os.path.exists(jdiff): + print("JDIFF doesn't exist.") + + make_dir(docs) + make_dir(comments) + make_dir(jdiff_com) + make_dir(tag_comments) + make_dir(jdiff_tag_com) + make_dir("jdiff-logs") + log = open("jdiff-logs/COMPARE-" + module.name + ".log", "w") + cmd = ["javadoc", + "-doclet", "jdiff.JDiff", + "-docletpath", jdiff, + "-d", docs, + "-oldapi", oldapi, + "-newapi", newapi, + "-script", + null_file] + jdiff = subprocess.Popen(cmd, stdout=log, stderr=log) + jdiff.wait() + log.close() + code = jdiff.returncode + print("Compared XML for " + module.name) + if code == NO_CHANGES: + print(" No API changes") + elif code == COMPATIBLE: + print(" API Changes are backwards compatible") + elif code == NON_COMPATIBLE: + print(" API Changes are not backwards compatible") + else: + print(" *Error in XML, most likely an empty module") + sys.stdout.flush() + return code + +# Generate the jdiff xml for the given module +# path: path to the autopsy source +# module: Module object +# name: api name for jdiff +def gen_xml(path, modules, name): + for module in modules: + # If its the regression test, the source is in the "test" dir + if module.name == "Testing": + src = os.path.join(path, module.name, "test", "qa-functional", "src") + else: + src = os.path.join(path, module.name, "src") + # xerces = os.path.abspath("./lib/xerces.jar") + xml_out = fix_path(os.path.abspath("./build/jdiff-xml/" + name + "-" + module.name)) + jdiff = fix_path(os.path.abspath("./thirdparty/jdiff/v-custom/jdiff.jar")) + make_dir("build/jdiff-xml") + make_dir("jdiff-logs") + log = open("jdiff-logs/GEN_XML-" + name + "-" + module.name + ".log", "w") + cmd = ["javadoc", + "-doclet", "jdiff.JDiff", + "-docletpath", jdiff, # ;" + xerces, <-- previous problems required this + "-apiname", xml_out, # leaving it in just in case it's needed once again + "-sourcepath", fix_path(src)] + cmd = cmd + get_packages(src) + jdiff = subprocess.Popen(cmd, stdout=log, stderr=log) + jdiff.wait() + log.close() + print("Generated XML for " + name + " " + module.name) + sys.stdout.flush() + +# Find all the modules in the given path +def find_modules(path): + modules = [] + # Step into each folder in the given path and + # see if it has manifest.mf - if so, it's a module + for dir in os.listdir(path): + directory = os.path.join(path, dir) + if os.path.isdir(directory): + for file in os.listdir(directory): + if file == "manifest.mf": + modules.append(Module(dir, None, None)) + return modules + +# Detects the differences between the source and tag modules +def module_diff(source_modules, tag_modules): + added_modules = [x for x in source_modules if x not in tag_modules] + removed_modules = [x for x in tag_modules if x not in source_modules] + similar_modules = [x for x in source_modules if x in tag_modules] + + added_modules = (added_modules if added_modules else []) + removed_modules = (removed_modules if removed_modules else []) + similar_modules = (similar_modules if similar_modules else []) + return similar_modules, added_modules, removed_modules + +# Reads the previous tag from NEWS.txt +def get_tag(sourcepath): + news = open(sourcepath + "/NEWS.txt", "r") + second_instance = False + for line in news: + if "----------------" in line: + if second_instance: + ver = line.split("VERSION ")[1] + ver = ver.split(" -")[0] + return ("autopsy-" + ver).strip() + else: + second_instance = True + continue + news.close() + + +# ========================================== # +# Dependency Functions # +# ========================================== # + +# Write a new XML file, copying all the lines from projectxml +# and replacing the specification version for the code-name-base base +# with the supplied specification version spec +def set_dep_spec(projectxml, base, spec): + print(" Updating Specification version..") + orig = open(projectxml, "r") + f, abs_path = mkstemp() + new_file = open(abs_path, "w") + found_base = False + spacing = " " + sopen = "" + sclose = "\n" + for line in orig: + if base in line: + found_base = True + if found_base and sopen in line: + update = spacing + sopen + str(spec) + sclose + new_file.write(update) + else: + new_file.write(line) + new_file.close() + close(f) + orig.close() + remove(projectxml) + move(abs_path, projectxml) + +# Write a new XML file, copying all the lines from projectxml +# and replacing the release version for the code-name-base base +# with the supplied release version +def set_dep_release(projectxml, base, release): + print(" Updating Release version..") + orig = open(projectxml, "r") + f, abs_path = mkstemp() + new_file = open(abs_path, "w") + found_base = False + spacing = " " + ropen = "" + rclose = "\n" + for line in orig: + if base in line: + found_base = True + if found_base and ropen in line: + update = spacing + ropen + str(release) + rclose + new_file.write(update) + else: + new_file.write(line) + new_file.close() + close(f) + orig.close() + remove(projectxml) + move(abs_path, projectxml) + +# Return the dependency versions in the XML dependency node +def get_dep_versions(dep): + run_dependency = dep.getElementsByTagName("run-dependency")[0] + release_version = run_dependency.getElementsByTagName("release-version") + if release_version: + release_version = getTagText(release_version[0].childNodes) + specification_version = run_dependency.getElementsByTagName("specification-version") + if specification_version: + specification_version = getTagText(specification_version[0].childNodes) + return int(release_version), Spec(specification_version) + +# Given a code-name-base, see if it corresponds with any of our modules +def get_module_from_base(modules, code_name_base): + for module in modules: + if "org.sleuthkit.autopsy." + module.name.lower() == code_name_base: + return module + return None # If it didn't match one of our modules + +# Check the text between two XML tags +def getTagText(nodelist): + for node in nodelist: + if node.nodeType == node.TEXT_NODE: + return node.data + +# Check the projectxml for a dependency on any module in modules +def check_for_dependencies(projectxml, modules): + dom = parse(projectxml) + dep_list = dom.getElementsByTagName("dependency") + for dep in dep_list: + code_name_base = dep.getElementsByTagName("code-name-base")[0] + code_name_base = getTagText(code_name_base.childNodes) + module = get_module_from_base(modules, code_name_base) + if module: + print(" Found dependency on " + module.name) + release, spec = get_dep_versions(dep) + if release != module.release() and module.release() is not None: + set_dep_release(projectxml, code_name_base, module.release()) + else: print(" Release version is correct") + if spec != module.spec() and module.spec() is not None: + set_dep_spec(projectxml, code_name_base, module.spec()) + else: print(" Specification version is correct") + +# Given the module and the source directory, return +# the paths to the manifest and project properties files +def get_dependency_file(module, source): + projectxml = os.path.join(source, module.name, "nbproject", "project.xml") + if os.path.isfile(projectxml): + return projectxml + +# Verify/Update the dependencies for each module, basing the dependency +# version number off the versions in each module +def update_dependencies(modules, source): + for module in modules: + print("Checking the dependencies for " + module.name + "...") + projectxml = get_dependency_file(module, source) + if projectxml == None: + print(" Error finding project xml file") + else: + other = [x for x in modules] + check_for_dependencies(projectxml, other) + sys.stdout.flush() + +# ======================================== # +# Versioning Functions # +# ======================================== # + +# Return the specification version in the given project.properties/manifest.mf file +def get_specification(project, manifest): + try: + # Try to find it in the project file + # it will be there if impl version is set to append automatically + f = open(project, 'r') + for line in f: + if "spec.version.base" in line: + return Spec(line.split("=")[1].strip()) + f.close() + # If not found there, try the manifest file + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module-Specification-Version:" in line: + return Spec(line.split(": ")[1].strip()) + except Exception as e: + print("Error parsing Specification version for") + print(project) + print(e) + +# Set the specification version in the given project properties file +# but if it can't be found there, set it in the manifest file +def set_specification(project, manifest, num): + try: + # First try the project file + f = open(project, 'r') + for line in f: + if "spec.version.base" in line: + f.close() + replace(project, line, "spec.version.base=" + str(num) + "\n") + return + f.close() + # If it's not there, try the manifest file + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module-Specification-Version:" in line: + f.close() + replace(manifest, line, "OpenIDE-Module-Specification-Version: " + str(num) + "\n") + return + # Otherwise we're out of luck + print(" Error finding the Specification version to update") + print(" " + manifest) + f.close() + except: + print(" Error incrementing Specification version for") + print(" " + project) + +# Return the implementation version in the given manifest.mf file +def get_implementation(manifest): + try: + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module-Implementation-Version" in line: + return int(line.split(": ")[1].strip()) + f.close() + except: + print("Error parsing Implementation version for") + print(manifest) + +# Set the implementation version in the given manifest file +def set_implementation(manifest, num): + try: + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module-Implementation-Version" in line: + f.close() + replace(manifest, line, "OpenIDE-Module-Implementation-Version: " + str(num) + "\n") + return + # If it isn't there, add it + f.close() + write_implementation(manifest, num) + except: + print(" Error incrementing Implementation version for") + print(" " + manifest) + +# Rewrite the manifest file to include the implementation version +def write_implementation(manifest, num): + f = open(manifest, "r") + contents = f.read() + contents = contents[:-2] + "OpenIDE-Module-Implementation-Version: " + str(num) + "\n\n" + f.close() + f = open(manifest, "w") + f.write(contents) + f.close() + +# Return the release version in the given manifest.mf file +def get_release(manifest): + try: + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module:" in line: + return int(line.split("/")[1].strip()) + f.close() + except: + #print("Error parsing Release version for") + #print(manifest) + return 0 + +# Set the release version in the given manifest file +def set_release(manifest, num): + try: + f = open(manifest, 'r') + for line in f: + if "OpenIDE-Module:" in line: + f.close() + index = line.index('/') - len(line) + 1 + newline = line[:index] + str(num) + replace(manifest, line, newline + "\n") + return + print(" Error finding the release version to update") + print(" " + manifest) + f.close() + except: + print(" Error incrementing release version for") + print(" " + manifest) + +# Given the module and the source directory, return +# the paths to the manifest and project properties files +def get_version_files(module, source): + manifest = os.path.join(source, module.name, "manifest.mf") + project = os.path.join(source, module.name, "nbproject", "project.properties") + if os.path.isfile(manifest) and os.path.isfile(project): + return manifest, project + +# Returns a the current version numbers for the module in source +def get_versions(module, source): + manifest, project = get_version_files(module, source) + if manifest == None or project == None: + print(" Error finding manifeset and project properties files") + return + spec = get_specification(project, manifest) + impl = get_implementation(manifest) + release = get_release(manifest) + return [spec, impl, release] + +# Update the version numbers for every module in modules +def update_versions(modules, source): + for module in modules: + versions = module.versions + manifest, project = get_version_files(module, source) + print("Updating " + module.name + "...") + if manifest == None or project == None: + print(" Error finding manifeset and project properties files") + return + if module.ret == COMPATIBLE: + versions = [versions[0].set(versions[0].increment()), versions[1] + 1, versions[2]] + set_specification(project, manifest, versions[0]) + set_implementation(manifest, versions[1]) + module.set_versions(versions) + elif module.ret == NON_COMPATIBLE: + versions = [versions[0].set(versions[0].overflow()), versions[1] + 1, versions[2] + 1] + set_specification(project, manifest, versions[0]) + set_implementation(manifest, versions[1]) + set_release(manifest, versions[2]) + module.set_versions(versions) + elif module.ret == NO_CHANGES: + versions = [versions[0], versions[1] + 1, versions[2]] + set_implementation(manifest, versions[1]) + module.set_versions(versions) + elif module.ret == None: + versions = [Spec("1.0"), 1, 1] + set_specification(project, manifest, versions[0]) + set_implementation(manifest, versions[1]) + set_release(manifest, versions[2]) + module.set_versions(versions) + sys.stdout.flush() + +# Given a list of the added modules, remove the modules +# which have the correct 'new module default' version number +def remove_correct_added(modules): + correct = [x for x in modules] + for module in modules: + if module.spec() == "1.0" or module.spec() == "0.0": + if module.impl() == 1: + if module.release() == 1 or module.release() == 0: + correct.remove(module) + return correct + +# ==================================== # +# Helper Functions # +# ==================================== # + +# Replace pattern with subst in given file +def replace(file, pattern, subst): + #Create temp file + fh, abs_path = mkstemp() + new_file = open(abs_path,'w') + old_file = open(file) + for line in old_file: + new_file.write(line.replace(pattern, subst)) + #close temp file + new_file.close() + close(fh) + old_file.close() + #Remove original file + remove(file) + #Move new file + move(abs_path, file) + +# Given a list of modules print the version numbers that need changing +def print_version_updates(modules): + f = open("gen_version.txt", "a") + for module in modules: + versions = module.versions + if module.ret == COMPATIBLE: + output = (module.name + ":\n") + output += ("\tSpecification:\t" + str(versions[0]) + "\t->\t" + str(versions[0].increment()) + "\n") + output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") + output += ("\tRelease:\tNo Change.\n") + output += ("\n") + print(output) + sys.stdout.flush() + f.write(output) + elif module.ret == NON_COMPATIBLE: + output = (module.name + ":\n") + output += ("\tSpecification:\t" + str(versions[0]) + "\t->\t" + str(versions[0].overflow()) + "\n") + output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") + output += ("\tRelease:\t" + str(versions[2]) + "\t->\t" + str(versions[2] + 1) + "\n") + output += ("\n") + print(output) + sys.stdout.flush() + f.write(output) + elif module.ret == ERROR: + output = (module.name + ":\n") + output += ("\t*Unable to detect necessary changes\n") + output += ("\tSpecification:\t" + str(versions[0]) + "\n") + output += ("\tImplementation:\t" + str(versions[1]) + "\n") + output += ("\tRelease:\t\t" + str(versions[2]) + "\n") + output += ("\n") + print(output) + f.write(output) + sys.stdout.flush() + elif module.ret == NO_CHANGES: + output = (module.name + ":\n") + if versions[1] is None: + output += ("\tImplementation: None\n") + else: + output += ("\tImplementation:\t" + str(versions[1]) + "\t->\t" + str(versions[1] + 1) + "\n") + output += ("\n") + print(output) + sys.stdout.flush() + f.write(output) + elif module.ret is None: + output = ("Added " + module.name + ":\n") + if module.spec() != "1.0" and module.spec() != "0.0": + output += ("\tSpecification:\t" + str(module.spec()) + "\t->\t" + "1.0\n") + output += ("\n") + if module.impl() != 1: + output += ("\tImplementation:\t" + str(module.impl()) + "\t->\t" + "1\n") + output += ("\n") + if module.release() != 1 and module.release() != 0: + output += ("Release:\t\t" + str(module.release()) + "\t->\t" + "1\n") + output += ("\n") + print(output) + sys.stdout.flush() + f.write(output) + sys.stdout.flush() + f.close() + +# Changes cygwin paths to Windows +def fix_path(path): + if "cygdrive" in path: + new_path = path[11:] + return "C:/" + new_path + else: + return path + +# Print a 'title' +def printt(title): + print("\n" + title) + lines = "" + for letter in title: + lines += "-" + print(lines) + sys.stdout.flush() + +# Get a list of package names in the given path +# The path is expected to be of the form {base}/module/src +# +# NOTE: We currently only check for packages of the form +# org.sleuthkit.autopsy.x +# If we add other namespaces for commercial modules we will +# have to add a check here +def get_packages(path): + packages = [] + package_path = os.path.join(path, "org", "sleuthkit", "autopsy") + for folder in os.listdir(package_path): + package_string = "org.sleuthkit.autopsy." + packages.append(package_string + folder) + return packages + +# Create the given directory, if it doesn't already exist +def make_dir(dir): + try: + if not os.path.isdir(dir): + os.mkdir(dir) + if os.path.isdir(dir): + return True + return False + except: + print("Exception thrown when creating directory") + return False + +# Delete the given directory, and make sure it is deleted +def del_dir(dir): + try: + if os.path.isdir(dir): + shutil.rmtree(dir, ignore_errors=False, onerror=handleRemoveReadonly) + if os.path.isdir(dir): + return False + else: + return True + return True + except: + print("Exception thrown when deleting directory") + traceback.print_exc() + return False + +# Handle any permisson errors thrown by shutil.rmtree +def handleRemoveReadonly(func, path, exc): + excvalue = exc[1] + if func in (os.rmdir, os.remove) and excvalue.errno == errno.EACCES: + os.chmod(path, stat.S_IRWXU| stat.S_IRWXG| stat.S_IRWXO) # 0777 + func(path) + else: + raise + +# Run git clone and git checkout for the tag +def do_git(tag, tag_dir): + try: + printt("Cloning Autopsy tag " + tag + " into dir " + tag_dir + " (this could take a while)...") + subprocess.call(["git", "clone", "https://github.com/sleuthkit/autopsy.git", tag_dir], + stdout=subprocess.PIPE) + printt("Checking out tag " + tag + "...") + subprocess.call(["git", "checkout", tag], + stdout=subprocess.PIPE, + cwd=tag_dir) + return True + except Exception as ex: + print("Error cloning and checking out Autopsy: ", sys.exc_info()[0]) + print(str(ex)) + print("The terminal you are using most likely does not recognize git commands.") + return False + +# Get the flags from argv +def args(): + try: + sys.argv.pop(0) + while sys.argv: + arg = sys.argv.pop(0) + if arg == "-h" or arg == "--help": + return 1 + elif arg == "-t" or arg == "--tag": + global tag + tag = sys.argv.pop(0) + elif arg == "-s" or arg == "--source": + global source + source = sys.argv.pop(0) + elif arg == "-d" or arg == "--dir": + global docdir + docdir = sys.argv.pop(0) + elif arg == "-a" or arg == "--auto": + global dry + dry = False + else: + raise Exception() + except: + pass + +# Print script run info +def printinfo(): + global tag + global source + global docdir + global dry + printt("Release script information:") + if source is None: + source = fix_path(os.path.abspath(".")) + print("Using source directory:\n " + source) + if tag is None: + tag = get_tag(source) + print("Checking out to tag:\n " + tag) + if docdir is None: + docdir = fix_path(os.path.abspath("./jdiff-javadocs")) + print("Generating jdiff JavaDocs in:\n " + docdir) + if dry is True: + print("Dry run: will not auto-update version numbers") + sys.stdout.flush() + +# Print the script's usage/help +def usage(): + return \ + """ + USAGE: + Compares the API of the current Autopsy source code with a previous + tagged version. By default, it will detect the previous tag from + the NEWS file and will not update the versions in the source code. + + OPTIONAL FLAGS: + -t --tag Specify a previous tag to compare to. + Otherwise the NEWS file will be used. + + -d --dir The output directory for the jdiff JavaDocs. If no + directory is given, the default is jdiff-javadocs/{module}. + + -s --source The directory containing Autopsy's source code. + + -a --auto Automatically update version numbers (not dry). + + -h --help Prints this usage. + """ + +# ==================================== # +# Main Functionality # +# ==================================== # + +# Where the magic happens +def main(): + global tag; global source; global docdir; global dry + tag = None; source = None; docdir = None; dry = True + + ret = args() + if ret: + print(usage()) + return 0 + printinfo() + + # ----------------------------------------------- + # 1) Clone Autopsy, checkout to given tag/commit + # 2) Get the modules in the clone and the source + # 3) Generate the xml comparison + # ----------------------------------------------- + if not del_dir("./build/" + tag): + print("\n\n=========================================") + print(" Failed to delete previous Autopsy clone.") + print(" Unable to continue...") + print("=========================================") + return 1 + tag_dir = os.path.abspath("./build/" + tag) + if not do_git(tag, tag_dir): + return 1 + sys.stdout.flush() + + tag_modules = find_modules(tag_dir) + source_modules = find_modules(source) + + printt("Generating jdiff XML reports...") + apiname_tag = tag + apiname_cur = "current" + gen_xml(tag_dir, tag_modules, apiname_tag) + gen_xml(source, source_modules, apiname_cur) + + printt("Deleting cloned Autopsy directory...") + print("Clone successfully deleted" if del_dir(tag_dir) else "Failed to delete clone") + sys.stdout.flush() + + # ----------------------------------------------------- + # 1) Seperate modules into added, similar, and removed + # 2) Compare XML for each module + # ----------------------------------------------------- + printt("Comparing modules found...") + similar_modules, added_modules, removed_modules = module_diff(source_modules, tag_modules) + if added_modules or removed_modules: + for m in added_modules: + print("+ Added " + m.name) + sys.stdout.flush() + for m in removed_modules: + print("- Removed " + m.name) + sys.stdout.flush() + else: + print("No added or removed modules") + sys.stdout.flush() + + printt("Comparing jdiff outputs...") + for module in similar_modules: + module.set_ret(compare_xml(module, apiname_tag, apiname_cur)) + print("Refer to the jdiff-javadocs folder for more details") + + # ------------------------------------------------------------ + # 1) Do versioning + # 2) Auto-update version numbers in files and the_modules list + # 3) Auto-update dependencies + # ------------------------------------------------------------ + printt("Auto-detecting version numbers and changes...") + for module in added_modules: + module.set_versions(get_versions(module, source)) + for module in similar_modules: + module.set_versions(get_versions(module, source)) + + added_modules = remove_correct_added(added_modules) + the_modules = similar_modules + added_modules + print_version_updates(the_modules) + + if not dry: + printt("Auto-updating version numbers...") + update_versions(the_modules, source) + print("All auto-updates complete") + + printt("Detecting and auto-updating dependencies...") + update_dependencies(the_modules, source) + + printt("Deleting jdiff XML...") + xml_dir = os.path.abspath("./build/jdiff-xml") + print("XML successfully deleted" if del_dir(xml_dir) else "Failed to delete XML") + + print("\n--- Script completed successfully ---") + return 0 + +# Start off the script +if __name__ == "__main__": + sys.exit(main())