Search in PDF Files (#2838)

Co-authored-by: braunch <[email protected]> Co-authored-by: Oliver Kopp <[email protected]> Co-authored-by: Benedikt Tutzer <[email protected]> Co-authored-by: Carl Christian Snethlage <[email protected]> Co-authored-by: Christoph <[email protected]>
JabRef · Jul 14, 2021 · ddce573 · ddce573
1 parent 477118c
commit ddce573
Show file tree

Hide file tree

Showing 65 changed files with 1,894 additions and 291 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,8 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 
 ### Added
 
+- We added a fulltext search feature. [#2838](https://github.com/JabRef/jabref/pull/2838)
+
 ### Changed
 
 ### Fixed

diff --git a/build.gradle b/build.gradle
@@ -142,10 +142,6 @@ dependencies {
     antlr4 'org.antlr:antlr4:4.9.2'
     implementation 'org.antlr:antlr4-runtime:4.9.2'
 
-    implementation (group: 'org.apache.lucene', name: 'lucene-queryparser', version: '8.9.0') {
-        exclude group: 'org.apache.lucene', module: 'lucene-sandbox'
-    }
-
     implementation group: 'org.eclipse.jgit', name: 'org.eclipse.jgit', version: '5.12.0.202106070339-r'
 
     implementation group: 'com.fasterxml.jackson.dataformat', name: 'jackson-dataformat-yaml', version: '2.12.4'
@@ -209,6 +205,8 @@ dependencies {
     implementation 'com.vladsch.flexmark:flexmark-ext-gfm-strikethrough:0.62.2'
     implementation 'com.vladsch.flexmark:flexmark-ext-gfm-tasklist:0.62.2'
 
+    implementation group: 'net.harawata', name: 'appdirs', version: '1.2.1'
+
     testImplementation 'io.github.classgraph:classgraph:4.8.110'
     testImplementation 'org.junit.jupiter:junit-jupiter:5.7.2'
     testRuntimeOnly 'org.junit.vintage:junit-vintage-engine:5.7.2'

diff --git a/external-libraries.md b/external-libraries.md
@@ -310,7 +310,7 @@ License: Apache-2.0
 ```
 
 ```yaml
-Id:      org.apache.lucene:lucene-ueryparser
+Id:      org.apache.lucene:lucene-queryparser
 Project: Apache Lucene
 URL:     https://lucene.apache.org/
 License: Apache-2.0
@@ -567,6 +567,9 @@ org.apache.logging.log4j:log4j-slf4j18-impl:3.0.0-SNAPSHOT
 org.apache.lucene:lucene-core:8.9.0
 org.apache.lucene:lucene-queries:8.9.0
 org.apache.lucene:lucene-queryparser:8.9.0
+org.apache.lucene:lucene-analyzers-common:8.9.0
+org.apache.lucene:lucene-backward-codecs:8.9.0
+org.apache.lucene:lucene-highlighter:8.9.0
 org.apache.pdfbox:fontbox:2.0.24
 org.apache.pdfbox:pdfbox:2.0.24
 org.apache.pdfbox:xmpbox:2.0.24

diff --git a/lib/lucene.jar b/lib/lucene.jar
diff --git a/lucene-jar/lib/build.gradle b/lucene-jar/lib/build.gradle
@@ -0,0 +1,23 @@
+plugins {
+    id 'java-library'
+    id 'com.github.johnrengelman.shadow' version '7.0.0'
+}
+
+repositories {
+    mavenCentral()
+}
+
+shadowJar {
+    mergeServiceFiles()
+}
+
+dependencies {
+    implementation 'org.apache.lucene:lucene-core:8.9.0'
+    implementation ('org.apache.lucene:lucene-queryparser:8.9.0') {
+        exclude module: "lucene-sandbox"
+    }
+    implementation 'org.apache.lucene:lucene-queries:8.9.0'
+    implementation 'org.apache.lucene:lucene-analyzers-common:8.9.0'
+    implementation 'org.apache.lucene:lucene-backward-codecs:8.9.0'
+    implementation 'org.apache.lucene:lucene-highlighter:8.9.0'
+}
diff --git a/lucene-jar/settings.gradle b/lucene-jar/settings.gradle
@@ -0,0 +1,11 @@
+/*
+ * This file was generated by the Gradle 'init' task.
+ *
+ * The settings file is used to specify which projects to include in your build.
+ *
+ * Detailed information about configuring a multi-project build in Gradle can be found
+ * in the user manual at https://docs.gradle.org/7.0.2/userguide/multi_project_builds.html
+ */
+
+rootProject.name = 'lucene-jar'
+include('lib')
diff --git a/src/jmh/java/org/jabref/benchmarks/Benchmarks.java b/src/jmh/java/org/jabref/benchmarks/Benchmarks.java
@@ -3,6 +3,7 @@
 import java.io.IOException;
 import java.io.StringReader;
 import java.io.StringWriter;
+import java.util.EnumSet;
 import java.util.List;
 import java.util.Random;
 import java.util.stream.Collectors;
@@ -28,6 +29,7 @@
 import org.jabref.model.groups.KeywordGroup;
 import org.jabref.model.groups.WordKeywordGroup;
 import org.jabref.model.metadata.MetaData;
+import org.jabref.model.search.rules.SearchRules.SearchFlags;
 import org.jabref.model.util.DummyFileUpdateMonitor;
 import org.jabref.preferences.JabRefPreferences;
 
@@ -93,14 +95,14 @@ public String write() throws Exception {
     @Benchmark
     public List<BibEntry> search() {
         // FIXME: Reuse SearchWorker here
-        SearchQuery searchQuery = new SearchQuery("Journal Title 500", false, false);
+        SearchQuery searchQuery = new SearchQuery("Journal Title 500", EnumSet.noneOf(SearchFlags.class));
         return database.getEntries().stream().filter(searchQuery::isMatch).collect(Collectors.toList());
     }
 
     @Benchmark
     public List<BibEntry> parallelSearch() {
         // FIXME: Reuse SearchWorker here
-        SearchQuery searchQuery = new SearchQuery("Journal Title 500", false, false);
+        SearchQuery searchQuery = new SearchQuery("Journal Title 500", EnumSet.noneOf(SearchFlags.class));
         return database.getEntries().parallelStream().filter(searchQuery::isMatch).collect(Collectors.toList());
     }
 

diff --git a/src/main/java/module-info.java b/src/main/java/module-info.java
@@ -95,10 +95,10 @@
     requires flexmark.util.ast;
     requires flexmark.util.data;
     requires com.h2database.mvstore;
-    requires lucene.queryparser;
-    requires lucene.core;
+    requires lucene;
     requires org.eclipse.jgit;
     requires com.fasterxml.jackson.databind;
     requires com.fasterxml.jackson.dataformat.yaml;
     requires com.fasterxml.jackson.datatype.jsr310;
+    requires net.harawata.appdirs;
 }
diff --git a/src/main/java/org/jabref/cli/ArgumentProcessor.java b/src/main/java/org/jabref/cli/ArgumentProcessor.java
@@ -343,8 +343,7 @@ private boolean exportMatches(List<ParserResult> loaded) {
         BibDatabase dataBase = pr.getDatabase();
 
         SearchPreferences searchPreferences = Globals.prefs.getSearchPreferences();
-        SearchQuery query = new SearchQuery(searchTerm, searchPreferences.isCaseSensitive(),
-                searchPreferences.isRegularExpression());
+        SearchQuery query = new SearchQuery(searchTerm, searchPreferences.getSearchFlags());
         List<BibEntry> matches = new DatabaseSearcher(query, dataBase).getMatches();
 
         // export matches

diff --git a/src/main/java/org/jabref/gui/JabRefFrame.java b/src/main/java/org/jabref/gui/JabRefFrame.java
@@ -106,6 +106,7 @@
 import org.jabref.gui.push.PushToApplicationAction;
 import org.jabref.gui.push.PushToApplicationsManager;
 import org.jabref.gui.search.GlobalSearchBar;
+import org.jabref.gui.search.RebuildFulltextSearchIndexAction;
 import org.jabref.gui.shared.ConnectToSharedDatabaseCommand;
 import org.jabref.gui.shared.PullChangesFromSharedAction;
 import org.jabref.gui.slr.ExistingStudySearchAction;
@@ -819,7 +820,11 @@ private MenuBar createMenu() {
                 pushToApplicationMenuItem,
                 new SeparatorMenuItem(),
                 factory.createMenuItem(StandardActions.START_NEW_STUDY, new StartNewStudyAction(this, Globals.getFileUpdateMonitor(), Globals.TASK_EXECUTOR, prefs)),
-                factory.createMenuItem(StandardActions.SEARCH_FOR_EXISTING_STUDY, new ExistingStudySearchAction(this, Globals.getFileUpdateMonitor(), Globals.TASK_EXECUTOR, prefs))
+                factory.createMenuItem(StandardActions.SEARCH_FOR_EXISTING_STUDY, new ExistingStudySearchAction(this, Globals.getFileUpdateMonitor(), Globals.TASK_EXECUTOR, prefs)),
+
+                new SeparatorMenuItem(),
+
+                factory.createMenuItem(StandardActions.REBUILD_FULLTEXT_SEARCH_INDEX, new RebuildFulltextSearchIndexAction(stateManager, this::getCurrentLibraryTab, dialogService, prefs.getFilePreferences()))
         );
 
         SidePaneComponent webSearch = sidePaneManager.getComponent(SidePaneType.WEB_SEARCH);

diff --git a/src/main/java/org/jabref/gui/JabRefMain.java b/src/main/java/org/jabref/gui/JabRefMain.java
@@ -1,6 +1,12 @@
 package org.jabref.gui;
 
+import java.io.File;
+import java.io.IOException;
 import java.net.Authenticator;
+import java.nio.file.DirectoryStream;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.util.Comparator;
 
 import javafx.application.Application;
 import javafx.application.Platform;
@@ -20,6 +26,7 @@
 import org.jabref.logic.remote.client.RemoteClient;
 import org.jabref.logic.util.OS;
 import org.jabref.migrations.PreferencesMigrations;
+import org.jabref.model.database.BibDatabaseContext;
 import org.jabref.model.database.BibDatabaseMode;
 import org.jabref.preferences.JabRefPreferences;
 import org.jabref.preferences.PreferencesService;
@@ -59,6 +66,8 @@ public void start(Stage mainStage) {
 
             applyPreferences(preferences);
 
+            clearOldSearchIndices();
+
             try {
                 // Process arguments
                 ArgumentProcessor argumentProcessor = new ArgumentProcessor(arguments, ArgumentProcessor.Mode.INITIAL_START);
@@ -139,4 +148,24 @@ private static void configureProxy(ProxyPreferences proxyPreferences) {
             Authenticator.setDefault(new ProxyAuthenticator());
         }
     }
+
+    private static void clearOldSearchIndices() {
+        Path currentIndexPath = BibDatabaseContext.getFulltextIndexBasePath();
+        Path appData = currentIndexPath.getParent();
+
+        try (DirectoryStream<Path> stream = Files.newDirectoryStream(appData)) {
+            for (Path path : stream) {
+                if (Files.isDirectory(path) && !path.equals(currentIndexPath)) {
+                    LOGGER.info("Deleting out-of-date fulltext search index at {}.", path);
+                    Files.walk(path)
+                         .sorted(Comparator.reverseOrder())
+                         .map(Path::toFile)
+                         .forEach(File::delete);
+
+                }
+            }
+        } catch (IOException e) {
+            LOGGER.error("Could not access app-directory at {}", appData, e);
+        }
+    }
 }
diff --git a/src/main/java/org/jabref/gui/LibraryTab.java b/src/main/java/org/jabref/gui/LibraryTab.java
@@ -1,6 +1,7 @@
 package org.jabref.gui;
 
 import java.io.File;
+import java.io.IOException;
 import java.nio.file.Path;
 import java.util.ArrayList;
 import java.util.Collections;
@@ -43,8 +44,11 @@
 import org.jabref.logic.autosaveandbackup.BackupManager;
 import org.jabref.logic.citationstyle.CitationStyleCache;
 import org.jabref.logic.importer.ParserResult;
+import org.jabref.logic.importer.util.FileFieldParser;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.logic.pdf.FileAnnotationCache;
+import org.jabref.logic.pdf.search.indexing.IndexingTaskManager;
+import org.jabref.logic.pdf.search.indexing.PdfIndexer;
 import org.jabref.logic.search.SearchQuery;
 import org.jabref.logic.shared.DatabaseLocation;
 import org.jabref.logic.util.UpdateField;
@@ -56,10 +60,13 @@
 import org.jabref.model.database.event.EntriesAddedEvent;
 import org.jabref.model.database.event.EntriesRemovedEvent;
 import org.jabref.model.entry.BibEntry;
+import org.jabref.model.entry.LinkedFile;
 import org.jabref.model.entry.event.EntriesEventSource;
 import org.jabref.model.entry.event.EntryChangedEvent;
+import org.jabref.model.entry.event.FieldChangedEvent;
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.entry.field.FieldFactory;
+import org.jabref.model.entry.field.StandardField;
 import org.jabref.preferences.PreferencesService;
 
 import com.google.common.eventbus.Subscribe;
@@ -101,6 +108,8 @@ public class LibraryTab extends Tab {
     // initializing it so we prevent NullPointerException
     private BackgroundTask<ParserResult> dataLoadingTask = BackgroundTask.wrap(() -> null);
 
+    private IndexingTaskManager indexingTaskManager = new IndexingTaskManager(Globals.TASK_EXECUTOR);
+
     public LibraryTab(JabRefFrame frame,
                       PreferencesService preferencesService,
                       BibDatabaseContext bibDatabaseContext,
@@ -125,6 +134,7 @@ public LibraryTab(JabRefFrame frame,
         setupAutoCompletion();
 
         this.getDatabase().registerListener(new SearchListener());
+        this.getDatabase().registerListener(new IndexUpdateListener());
         this.getDatabase().registerListener(new EntriesRemovedListener());
 
         // ensure that at each addition of a new entry, the entry is added to the groups interface
@@ -332,6 +342,8 @@ public void updateTabTitle(boolean isChanged) {
             textProperty().setValue(tabTitle.toString());
             setTooltip(new Tooltip(toolTipText.toString()));
         });
+
+        indexingTaskManager.updateDatabaseName(tabTitle.toString());
     }
 
     private List<String> collectAllDatabasePaths() {
@@ -846,4 +858,63 @@ public void listen(EntriesRemovedEvent removedEntriesEvent) {
             DefaultTaskExecutor.runInJavaFXThread(() -> frame.getGlobalSearchBar().performSearch());
         }
     }
+
+    private class IndexUpdateListener {
+
+        public IndexUpdateListener() {
+            try {
+                indexingTaskManager.addToIndex(PdfIndexer.of(bibDatabaseContext, preferencesService.getFilePreferences()), bibDatabaseContext);
+            } catch (IOException e) {
+                LOGGER.error("Cannot access lucene index", e);
+            }
+        }
+
+        @Subscribe
+        public void listen(EntriesAddedEvent addedEntryEvent) {
+            try {
+                PdfIndexer pdfIndexer = PdfIndexer.of(bibDatabaseContext, preferencesService.getFilePreferences());
+                for (BibEntry addedEntry : addedEntryEvent.getBibEntries()) {
+                    indexingTaskManager.addToIndex(pdfIndexer, addedEntry, bibDatabaseContext);
+                }
+            } catch (IOException e) {
+                LOGGER.error("Cannot access lucene index", e);
+            }
+        }
+
+        @Subscribe
+        public void listen(EntriesRemovedEvent removedEntriesEvent) {
+            try {
+                PdfIndexer pdfIndexer = PdfIndexer.of(bibDatabaseContext, preferencesService.getFilePreferences());
+                for (BibEntry removedEntry : removedEntriesEvent.getBibEntries()) {
+                    indexingTaskManager.removeFromIndex(pdfIndexer, removedEntry);
+                }
+            } catch (IOException e) {
+                LOGGER.error("Cannot access lucene index", e);
+            }
+        }
+
+        @Subscribe
+        public void listen(FieldChangedEvent fieldChangedEvent) {
+            if (fieldChangedEvent.getField().equals(StandardField.FILE)) {
+                List<LinkedFile> oldFileList = FileFieldParser.parse(fieldChangedEvent.getOldValue());
+                List<LinkedFile> newFileList = FileFieldParser.parse(fieldChangedEvent.getNewValue());
+
+                List<LinkedFile> addedFiles = new ArrayList<>(newFileList);
+                addedFiles.remove(oldFileList);
+                List<LinkedFile> removedFiles = new ArrayList<>(oldFileList);
+                removedFiles.remove(newFileList);
+
+                try {
+                    indexingTaskManager.addToIndex(PdfIndexer.of(bibDatabaseContext, preferencesService.getFilePreferences()), fieldChangedEvent.getBibEntry(), addedFiles, bibDatabaseContext);
+                    indexingTaskManager.removeFromIndex(PdfIndexer.of(bibDatabaseContext, preferencesService.getFilePreferences()), fieldChangedEvent.getBibEntry(), removedFiles);
+                } catch (IOException e) {
+                    LOGGER.warn("I/O error when writing lucene index", e);
+                }
+            }
+        }
+    }
+
+    public IndexingTaskManager getIndexingTaskManager() {
+        return indexingTaskManager;
+    }
 }
diff --git a/src/main/java/org/jabref/gui/actions/StandardActions.java b/src/main/java/org/jabref/gui/actions/StandardActions.java
@@ -30,6 +30,7 @@ public enum StandardActions implements Action {
     DELETE(Localization.lang("Delete"), IconTheme.JabRefIcons.DELETE_ENTRY),
     DELETE_ENTRY(Localization.lang("Delete Entry"), IconTheme.JabRefIcons.DELETE_ENTRY, KeyBinding.DELETE_ENTRY),
     SEND_AS_EMAIL(Localization.lang("Send as email"), IconTheme.JabRefIcons.EMAIL),
+    REBUILD_FULLTEXT_SEARCH_INDEX(Localization.lang("Rebuild fulltext search index"), IconTheme.JabRefIcons.FILE),
     OPEN_EXTERNAL_FILE(Localization.lang("Open file"), IconTheme.JabRefIcons.FILE, KeyBinding.OPEN_FILE),
     OPEN_URL(Localization.lang("Open URL or DOI"), IconTheme.JabRefIcons.WWW, KeyBinding.OPEN_URL_OR_DOI),
     SEARCH_SHORTSCIENCE(Localization.lang("Search ShortScience")),

diff --git a/src/main/java/org/jabref/gui/entryeditor/EntryEditor.java b/src/main/java/org/jabref/gui/entryeditor/EntryEditor.java
@@ -31,6 +31,7 @@
 import org.jabref.gui.StateManager;
 import org.jabref.gui.citationkeypattern.GenerateCitationKeySingleAction;
 import org.jabref.gui.entryeditor.fileannotationtab.FileAnnotationTab;
+import org.jabref.gui.entryeditor.fileannotationtab.FulltextSearchResultsTab;
 import org.jabref.gui.externalfiles.ExternalFilesEntryLinker;
 import org.jabref.gui.externalfiletype.ExternalFileTypes;
 import org.jabref.gui.help.HelpAction;
@@ -267,6 +268,8 @@ private List<EntryEditorTab> createTabs() {
         // LaTeX citations tab
         entryEditorTabs.add(new LatexCitationsTab(databaseContext, preferencesService, taskExecutor, dialogService));
 
+        entryEditorTabs.add(new FulltextSearchResultsTab(stateManager, preferencesService.getTheme(), preferencesService.getFilePreferences()));
+
         return entryEditorTabs;
     }