Bibtexextractor

AUTHORS

@@ -210,3 +210,4 @@ Yang Zongze
 Yara Grassi Gouffon
 Yifan Peng
 Zhang Liang
+Nikita Borovikov

CHANGELOG.md

@@ -69,6 +69,7 @@ We refer to [GitHub issues](https://github.com/JabRef/jabref/issues) by using `#
 - The Medline fetcher now normalizes the author names according to the BibTeX-Standard [#4345](https://github.com/JabRef/jabref/issues/4345)
 - We added an option on the Linked File Viewer to rename the attached file of an entry directly on the JabRef. [#4844](https://github.com/JabRef/jabref/issues/4844)
 - We added an option in the preference dialog box that allows user to enable helpful tooltips.[#3599](https://github.com/JabRef/jabref/issues/3599)
+- We add tool for extracting BibTeX entity from plain text
 - We moved the dropdown menu for selecting the push-application from the toolbar into the external application preferences. [#674](https://github.com/JabRef/jabref/issues/674)
 - We removed the alphabetical ordering of the custom tabs and updated the error message when trying to create a general field with a name containing an illegal character. [#5019](https://github.com/JabRef/jabref/issues/5019)
 - We added a context menu to the bib(la)tex-source-editor to copy'n'paste. [#5007](https://github.com/JabRef/jabref/pull/5007)

src/main/java/org/jabref/gui/JabRefFrame.java

@@ -54,6 +54,7 @@
 import org.jabref.gui.actions.OldDatabaseCommandWrapper;
 import org.jabref.gui.actions.SimpleCommand;
 import org.jabref.gui.actions.StandardActions;
+import org.jabref.gui.bibtexextractor.ExtractBibtexAction;
 import org.jabref.gui.auximport.NewSubLibraryAction;
 import org.jabref.gui.bibtexkeypattern.BibtexKeyPatternAction;
 import org.jabref.gui.contentselector.ManageContentSelectorAction;
@@ -774,6 +775,7 @@ private MenuBar createMenu() {
                 factory.createMenuItem(StandardActions.FIND_UNLINKED_FILES, new FindUnlinkedFilesAction(this, stateManager)),
                 factory.createMenuItem(StandardActions.WRITE_XMP, new OldDatabaseCommandWrapper(Actions.WRITE_XMP, this, stateManager)),
                 factory.createMenuItem(StandardActions.COPY_LINKED_FILES, new CopyFilesAction(stateManager, this.getDialogService())),
+                factory.createMenuItem(StandardActions.EXTRACT_BIBTEX, new ExtractBibtexAction(this)),
 
                 new SeparatorMenuItem(),
 

src/main/java/org/jabref/gui/actions/StandardActions.java

@@ -138,6 +138,7 @@ public enum StandardActions implements Action {
     DOWNLOAD_FULL_TEXT(Localization.lang("Search full text documents online"), IconTheme.JabRefIcons.FILE_SEARCH, KeyBinding.DOWNLOAD_FULL_TEXT),
     CLEANUP_ENTRIES(Localization.lang("Cleanup entries"), IconTheme.JabRefIcons.CLEANUP_ENTRIES, KeyBinding.CLEANUP),
     SET_FILE_LINKS(Localization.lang("Automatically set file links"), KeyBinding.AUTOMATICALLY_LINK_FILES),
+    EXTRACT_BIBTEX(Localization.lang("Extract BibTeX from plain text")),
 
     HELP(Localization.lang("Online help"), IconTheme.JabRefIcons.HELP, KeyBinding.HELP),
     HELP_KEY_PATTERNS(Localization.lang("Help on key patterns"), IconTheme.JabRefIcons.HELP, KeyBinding.HELP),

src/main/java/org/jabref/gui/bibtexextractor/BibtexExtractor.java

@@ -0,0 +1,181 @@
+package org.jabref.gui.bibtexextractor;
+
+import org.jabref.model.entry.BibEntry;
+import org.jabref.model.entry.BiblatexEntryType;
+import org.jabref.model.entry.BiblatexEntryTypes;
+import org.jabref.model.entry.FieldName;
+
+import java.lang.reflect.Array;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Calendar;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+public class BibtexExtractor {
+
+    private final static String authorTag = "[author_tag]";
+    private final static String urlTag = "[url_tag]";
+    private final static String yearTag = "[year_tag]";
+    private final static String pagesTag = "[pages_tag]";
+    private final static String titleTag = "[title_tag]";
+    private final static String journalTag = "[journal_tag]";
+
+    private final static String INITIALS_GROUP = "INITIALS";
+    private final static String LASTNAME_GROUP = "LASTNAME";
+
+    private ArrayList<String> urls = new ArrayList<>();
+    private ArrayList<String> authors = new ArrayList<>();
+    private String year = new String();
+    private String pages = new String();
+    private String title = new String();
+    private boolean isArticle = true;
+    private String journalOrPublisher = new String();
+
+    private static final Pattern urlPattern = Pattern.compile(
+            "(?:^|[\\W])((ht|f)tp(s?):\\/\\/|www\\.)" +
+            "(([\\w\\-]+\\.)+?([\\w\\-.~]+\\/?)*" +
+            "[\\p{Alnum}.,%_=?&#\\-+()\\[\\]\\*$~@!:/{};']*)",
+            Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
+
+    private static final Pattern yearPattern = Pattern.compile(
+            "\\d{4}",
+            Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
+
+    private static final Pattern authorPattern1 = Pattern.compile(
+            "(?<" + LASTNAME_GROUP + ">\\p{Lu}\\w+),?\\s(?<" + INITIALS_GROUP + ">(\\p{Lu}\\.\\s){1,2})" +
+            "\\s*(and|,|\\.)*",
+            Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
+
+    private static final Pattern authorPattern2 = Pattern.compile(
+            "(?<" + INITIALS_GROUP + ">(\\p{Lu}\\.\\s){1,2})(?<" + LASTNAME_GROUP + ">\\p{Lu}\\w+)" +
+            "\\s*(and|,|\\.)*",
+            Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
+
+    private static final Pattern pagesPattern = Pattern.compile(
+            "(p.)?\\s?\\d+(-\\d+)?",
+            Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
+
+
+    public BibEntry extract(String input){
+        String inputWithoutUrls = findUrls(input);
+        String inputWithoutAuthors = findAuthors(inputWithoutUrls);
+        String inputWithoutYear = findYear(inputWithoutAuthors);
+        String inputWithoutPages = findPages(inputWithoutYear);
+        String nonparsed = findParts(inputWithoutPages);
+        return GenerateEntity(nonparsed);
+    }
+
+    private BibEntry GenerateEntity(String input){
+        BiblatexEntryType type = isArticle ? BiblatexEntryTypes.ARTICLE : BiblatexEntryTypes.BOOK;
+        BibEntry extractedEntity = new BibEntry(type);
+        extractedEntity.setField(FieldName.AUTHOR, String.join(" and ", authors));
+        extractedEntity.setField(FieldName.URL, String.join(", ", urls));
+        extractedEntity.setField(FieldName.YEAR, year);
+        extractedEntity.setField(FieldName.PAGES, pages);
+        extractedEntity.setField(FieldName.TITLE, title);
+        if (isArticle){
+            extractedEntity.setField(FieldName.JOURNAL, journalOrPublisher);
+        }
+        else {
+            extractedEntity.setField(FieldName.PUBLISHER, journalOrPublisher);
+        }
+        extractedEntity.setField(FieldName.COMMENT, input);
+        return  extractedEntity;
+    }
+
+    private String findUrls(String input){
+        Matcher matcher = urlPattern.matcher(input);
+        while (matcher.find()) {
+            urls.add(input.substring(matcher.start(1), matcher.end()));
+        }
+        return fixSpaces(matcher.replaceAll(urlTag));
+    }
+
+    private String findYear(String input){
+        Matcher matcher = yearPattern.matcher(input);
+        while (matcher.find()){
+            String yearCandidate = input.substring(matcher.start(), matcher.end());
+            Integer intYearCandidate = Integer.parseInt(yearCandidate);
+            if (intYearCandidate > 1700 && intYearCandidate <= Calendar.getInstance().get(Calendar.YEAR)){
+                year = yearCandidate;
+                return fixSpaces(input.replace(year, yearTag));
+            }
+        }
+        return input;
+    }
+
+    private String findAuthors(String input){
+        String currentInput = findAuthorsByPattern(input, authorPattern1);
+        return findAuthorsByPattern(currentInput, authorPattern2);
+    }
+
+    private String findAuthorsByPattern(String input, Pattern pattern){
+        Matcher matcher = pattern.matcher(input);
+        while (matcher.find()) {
+            authors.add(GenerateAuthor(matcher.group(LASTNAME_GROUP), matcher.group(INITIALS_GROUP)));
+        }
+        return fixSpaces(matcher.replaceAll(authorTag));
+    }
+
+    private String GenerateAuthor(String lastName, String initials){
+        return lastName + ", " + initials;
+    }
+
+    private String findPages(String input){
+        Matcher matcher = pagesPattern.matcher(input);
+        if (matcher.find()){
+            pages = input.substring(matcher.start(1), matcher.end());
+        }
+        return fixSpaces(matcher.replaceFirst(pagesTag));
+    }
+
+    private String fixSpaces(String input){
+        return input.replaceAll("[,.!?;:]", "$0 ")
+                    .replaceAll("\\p{Lt}", " $0")
+                    .replaceAll("\\s+", " ").trim();
+    }
+
+    private String findParts(String input)
+    {
+        ArrayList<String> lastParts = new ArrayList<>();
+        String line = input;
+        int afterAuthorsIndex = input.lastIndexOf(authorTag);
+        if (afterAuthorsIndex == -1){
+            return input;
+        }
+        else {
+            afterAuthorsIndex += authorTag.length();
+        }
+        int delimiterIndex = input.lastIndexOf("//");
+        if (delimiterIndex != -1){
+            lastParts.add(input.substring(afterAuthorsIndex, delimiterIndex)
+                         .replace(yearTag, "")
+                         .replace(pagesTag, ""));
+            lastParts.addAll(Arrays.asList(input.substring(delimiterIndex + 2).split(",|\\.")));
+        }
+
+        else {
+            lastParts.addAll(Arrays.asList(input.substring(afterAuthorsIndex).split(",|\\.")));
+        }
+        int nonDigitParts = 0;
+        for (String part: lastParts) {
+            if (part.matches(".*\\d.*")){
+                break;
+            }
+            nonDigitParts++;
+        }
+        if (nonDigitParts > 0){
+            title = lastParts.get(0);
+            line.replace(title, titleTag);
+        }
+        if (nonDigitParts > 1){
+            journalOrPublisher = lastParts.get(1);
+            line.replace(journalOrPublisher, journalTag);
+        }
+        if (nonDigitParts > 2){
+            isArticle = false;
+        }
+        return fixSpaces(line);
+    }
+}

src/main/java/org/jabref/gui/bibtexextractor/ExtractBibtexAction.java

@@ -0,0 +1,19 @@
+package org.jabref.gui.bibtexextractor;
+
+import org.jabref.gui.JabRefFrame;
+import org.jabref.gui.actions.SimpleCommand;
+
+public class ExtractBibtexAction extends SimpleCommand {
+
+    private final JabRefFrame jabRefFrame;
+
+    public ExtractBibtexAction(JabRefFrame jabRefFrame) {
+        this.jabRefFrame = jabRefFrame;
+    }
+
+    @Override
+    public void execute() {
+        ExtractBibtexDialog dlg = new ExtractBibtexDialog(jabRefFrame);
+        dlg.showAndWait();
+    }
+}

src/main/java/org/jabref/gui/bibtexextractor/ExtractBibtexDialog.java

@@ -0,0 +1,72 @@
+package org.jabref.gui.bibtexextractor;
+
+import javafx.scene.control.*;
+import javafx.scene.layout.VBox;
+import org.jabref.Globals;
+import org.jabref.gui.JabRefFrame;
+import org.jabref.gui.util.BaseDialog;
+import org.jabref.logic.l10n.Localization;
+import org.jabref.model.entry.BibEntry;
+import org.jabref.model.entry.BiblatexEntryTypes;
+import org.jabref.model.entry.EntryType;
+
+import java.util.HashMap;
+import java.util.Map;
+
+/**
+ * GUI Dialog for the feature "Extract BibTeX from plain text".
+ */
+public class ExtractBibtexDialog extends BaseDialog<Void> {
+
+    private final JabRefFrame frame;
+    private TextArea textArea;
+    private Button buttonExtract;
+
+    public ExtractBibtexDialog(JabRefFrame frame) {
+        super();
+        this.setTitle(Localization.lang("Input text to parse"));
+        this.frame = frame;
+
+       initialize();
+    }
+
+    private void initialize(){
+        textArea = new TextArea();
+        textArea.setWrapText(true);
+        textArea.textProperty()
+                .addListener((observable, oldValue, newValue) -> buttonExtract.setDisable(newValue.isEmpty()));
+
+        VBox container = new VBox(20);
+        container.getChildren().addAll(
+                textArea);
+        container.setPrefWidth(600);
+
+        ButtonType buttonTypeGenerate = new ButtonType(Localization.lang("Extract"), ButtonBar.ButtonData.OK_DONE);
+        getDialogPane().getButtonTypes().setAll(
+                buttonTypeGenerate,
+                ButtonType.CANCEL
+        );
+
+        buttonExtract = (Button) getDialogPane().lookupButton(buttonTypeGenerate);
+        buttonExtract.setTooltip(new Tooltip((Localization.lang("Starts the extraction of the BibTeX entry"))));
+        buttonExtract.setDisable(true);
+        buttonExtract.setOnAction(e -> startExtraction());
+
+        getDialogPane().setContent(container);
+    }
+
+    private void startExtraction()
+    {
+        BibtexExtractor extractor = new BibtexExtractor();
+        BibEntry entity = extractor.extract(textArea.getText());
+        trackNewEntry(BiblatexEntryTypes.ARTICLE);
+        frame.getCurrentBasePanel().insertEntry(entity);
+    }
+
+    private void trackNewEntry(EntryType type) {
+        Map<String, String> properties = new HashMap<>();
+        properties.put("EntryType", type.getName());
+
+        Globals.getTelemetryClient().ifPresent(client -> client.trackEvent("NewEntry", properties, new HashMap<>()));
+    }
+}

src/main/resources/l10n/JabRef_en.properties

@@ -2074,6 +2074,12 @@ Accept\ changes=Accept changes
 Dismiss\ changes=Dismiss changes
 The\ library\ has\ been\ modified\ by\ another\ program.=The library has been modified by another program.
 
+Extract=Extract
+Extract\ BibTeX\ from\ plain\ text= Extract BibTeX from plain text
+Input\ text\ for\ parse=Input text to parse
+Starts\ the\ extraction\ of\ the\ BibTeX\ entry=Starts the extraction of the BibTeX entry
+
+Browser=Browser
 Execute\ command=Execute command
 Open\ File\ Browser=Open File Browser
 Use\ default\ file\ browser=Use default file browser