Do not trim or remove whitespace from the title based id fetcher (#4016)

* Do not trim text for TitleBasedFetcher
Fixes #4014

* add changelog

* add trimming epxlicit to fetchers
add some tests

* move doi trim to parse
add test

CHANGELOG.md

@@ -15,9 +15,10 @@ We refer to [GitHub issues](https://github.com/JabRef/jabref/issues) by using `#
 - We added a fetcher based on RFC-IDs. [#3971](https://github.com/JabRef/jabref/issues/3971)
 
 ### Fixed
-We fixed an issue where the export to clipboard functionality could not be invoked [#3994](https://github.com/JabRef/jabref/issues/3994)
-We fixed an issue with the migration of invalid Look and Feels [#3995, comment](https://github.com/JabRef/jabref/issues/3995#issuecomment-385649448)
-We fixed an issue where JabRef would no longer start, when the option "Override default font settings" was activated [#3986](https://github.com/JabRef/jabref/issues/3986)
+We fixed an issue where the export to clipboard functionality could not be invoked. [#3994](https://github.com/JabRef/jabref/issues/3994)
+We fixed an issue with the migration of invalid Look and Feels. [#3995, comment](https://github.com/JabRef/jabref/issues/3995#issuecomment-385649448)
+We fixed an issue where JabRef would no longer start, when the option "Override default font settings" was activated. [#3986](https://github.com/JabRef/jabref/issues/3986)
+We fixed an issue where JabRef removed whitespace from the Title-fetcher which resulting in no entries being found. [#4014](https://github.com/JabRef/jabref/issues/4014)
 We fixed an issue where fetched entries from the ACM fetcher could not be imported. [#4018](https://github.com/JabRef/jabref/issues/4018)
 
 ### Removed

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

@@ -73,6 +73,7 @@ public EntryTypeDialog(JabRefFrame frame) {
  setTitle(Localization.lang("Select entry type"));
 
  addWindowListener(new WindowAdapter() {
+
  @Override
  public void windowClosing(WindowEvent e) {
  cancelAction.actionPerformed(null);
@@ -246,7 +247,6 @@ static class TypeButton extends JButton implements Comparable<TypeButton> {
 
  private final EntryType type;
 
-
  TypeButton(String label, EntryType type) {
  super(label);
  this.type = type;
@@ -263,6 +263,7 @@ public EntryType getType() {
  }
 
  class CancelAction extends AbstractAction {
+
  public CancelAction() {
  super("Cancel");
  }
@@ -275,6 +276,7 @@ public void actionPerformed(ActionEvent e) {
  }
 
  private class FetcherWorker extends SwingWorker<Optional<BibEntry>, Void> {
+
  private boolean fetcherException = false;
  private String fetcherExceptionMessage = "";
  private IdBasedFetcher fetcher = null;
@@ -288,10 +290,9 @@ protected Optional<BibEntry> doInBackground() throws Exception {
  generateButton.setText(Localization.lang("Searching..."));
  });
 
- Globals.prefs.put(JabRefPreferences.ID_ENTRY_GENERATOR,String.valueOf(comboBox.getSelectedItem()));
- searchID = idTextField.getText().trim();
- searchID = searchID.replaceAll(" ", "");
+ Globals.prefs.put(JabRefPreferences.ID_ENTRY_GENERATOR, String.valueOf(comboBox.getSelectedItem()));
  fetcher = WebFetchers.getIdBasedFetchers(Globals.prefs.getImportFormatPreferences()).get(comboBox.getSelectedIndex());
+ searchID = idTextField.getText();
  if (!searchID.isEmpty()) {
  try {
  bibEntry = fetcher.performSearchById(searchID);
@@ -311,7 +312,7 @@ protected void done() {
  if (result.isPresent()) {
  final BibEntry bibEntry = result.get();
  if ((DuplicateCheck.containsDuplicate(frame.getCurrentBasePanel().getDatabase(), bibEntry, frame.getCurrentBasePanel().getBibDatabaseContext().getMode()).isPresent())) {
-  //If there are duplicates starts ImportInspectionDialog
+  //If there are duplicates starts ImportInspectionDialog
  final BasePanel panel = (BasePanel) frame.getTabbedPane().getSelectedComponent();
 
  ImportInspectionDialog diag = new ImportInspectionDialog(frame, panel, Localization.lang("Import"), false);
@@ -321,7 +322,7 @@ protected void done() {
  diag.setVisible(true);
  diag.toFront();
  } else {
-  // Regenerate CiteKey of imported BibEntry
+  // Regenerate CiteKey of imported BibEntry
  new BibtexKeyGenerator(frame.getCurrentBasePanel().getBibDatabaseContext(), Globals.prefs.getBibtexKeyPatternPreferences()).generateAndSetKey(bibEntry);
  // Update Timestamps
  if (Globals.prefs.getTimestampPreferences().includeCreatedTimestamp()) {

src/main/java/org/jabref/logic/importer/fetcher/ArXiv.java

@@ -258,8 +258,10 @@ public List<BibEntry> performSearch(String query) throws FetcherException {
 
  @Override
  public Optional<BibEntry> performSearchById(String identifier) throws FetcherException {
- return searchForEntryById(identifier).map(
- (arXivEntry) -> arXivEntry.toBibEntry(importFormatPreferences.getKeywordSeparator()));
+ String cleanedIdentifier = identifier.trim();
+ cleanedIdentifier = identifier.replaceAll(" ", "");
+
+ return searchForEntryById(cleanedIdentifier).map((arXivEntry) -> arXivEntry.toBibEntry(importFormatPreferences.getKeywordSeparator()));
  }
 
  @Override

src/main/java/org/jabref/logic/importer/fetcher/DoiFetcher.java

@@ -45,7 +45,6 @@ public HelpFile getHelpPage() {
  @Override
  public Optional<BibEntry> performSearchById(String identifier) throws FetcherException {
  Optional<DOI> doi = DOI.parse(identifier);
-
  try {
  if (doi.isPresent()) {
  URL doiURL = new URL(doi.get().getURIAsASCIIString());

src/main/java/org/jabref/logic/importer/fetcher/IacrEprintFetcher.java

@@ -37,8 +37,10 @@ public class IacrEprintFetcher implements IdBasedFetcher {
 
  private static final Logger LOGGER = LoggerFactory.getLogger(IacrEprintFetcher.class);
  private static final Pattern DATE_FROM_WEBSITE_AFTER_2000_PATTERN = Pattern.compile("[a-z ]+(\\d{1,2} [A-Za-z][a-z]{2} \\d{4})");
- private static final DateTimeFormatter DATE_FORMAT_WEBSITE_AFTER_2000 = DateTimeFormatter.ofPattern("d MMM yyyy", Locale.US);
  private static final Pattern DATE_FROM_WEBSITE_BEFORE_2000_PATTERN = Pattern.compile("[A-Za-z ]+? ([A-Za-z][a-z]{2,10} \\d{1,2}(th|st|nd|rd)?, \\d{4})\\.?");
+ private static final Pattern WITHOUT_LETTERS_SPACE = Pattern.compile("[^0-9/]");
+
+ private static final DateTimeFormatter DATE_FORMAT_WEBSITE_AFTER_2000 = DateTimeFormatter.ofPattern("d MMM yyyy", Locale.US);
  private static final DateTimeFormatter DATE_FORMAT_WEBSITE_BEFORE_2000_LONG_MONTHS = DateTimeFormatter.ofPattern("MMMM d['th']['st']['nd']['rd'] yyyy", Locale.US);
  private static final DateTimeFormatter DATE_FORMAT_WEBSITE_BEFORE_2000_SHORT_MONTHS = DateTimeFormatter.ofPattern("MMM d['th']['st']['nd']['rd'] yyyy", Locale.US);
  private static final DateTimeFormatter DATE_FORMAT_BIBTEX = DateTimeFormatter.ISO_LOCAL_DATE;
@@ -55,7 +57,7 @@ public IacrEprintFetcher(ImportFormatPreferences prefs) {
 
  @Override
  public Optional<BibEntry> performSearchById(String identifier) throws FetcherException {
- String identifierWithoutLettersAndSpaces = identifier.replaceAll("[^0-9/]", " ").trim();
+ String identifierWithoutLettersAndSpaces = WITHOUT_LETTERS_SPACE.matcher(identifier).replaceAll(" ").trim();
 
  if (!IDENTIFIER_PREDICATE.test(identifierWithoutLettersAndSpaces)) {
  throw new FetcherException(Localization.lang("Invalid identifier: '%0'.", identifier));

src/main/java/org/jabref/model/entry/identifier/DOI.java

@@ -95,7 +95,9 @@ public DOI(String doi) {
  */
  public static Optional<DOI> parse(String doi) {
  try {
- return Optional.of(new DOI(doi));
+ String cleanedDOI = doi.trim();
+ cleanedDOI = doi.replaceAll(" ", "");
+ return Optional.of(new DOI(cleanedDOI));
  } catch (IllegalArgumentException | NullPointerException e) {
  return Optional.empty();
  }

src/test/java/org/jabref/logic/importer/fetcher/ArXivTest.java

@@ -168,6 +168,11 @@ public void searchEntryByIdWith4DigitsAndPrefix() throws Exception {
  assertEquals(Optional.of(sliceTheoremPaper), finder.performSearchById("arXiv:1405.2249"));
  }
 
+ @Test
+ public void searchEntryByIdWith4DigitsAndPrefixAndNotTrimmed() throws Exception {
+ assertEquals(Optional.of(sliceTheoremPaper), finder.performSearchById("arXiv : 1405. 2249"));
+ }
+
  @Test
  public void searchEntryByIdWith5Digits() throws Exception {
  assertEquals(Optional.of(
@@ -186,4 +191,5 @@ public void searchIdentifierForSlicePaper() throws Exception {
 
  assertEquals(ArXivIdentifier.parse("1405.2249v1"), finder.findIdentifier(sliceTheoremPaper));
  }
+
 }

src/test/java/org/jabref/logic/importer/fetcher/DoiFetcherTest.java

@@ -48,6 +48,7 @@ public void setUp() {
  bibEntryDecker2007.setField("doi", "10.1109/icws.2007.59");
  }
 
+
  @Test
  public void testGetName() {
  assertEquals("DOI", fetcher.getName());
@@ -80,4 +81,10 @@ public void testPerformSearchInvalidDOI() {
  assertThrows(FetcherException.class, () -> fetcher.performSearchById("10.1002/9781118257517F"));
 
  }
+
+ @Test
+ public void testPerformSearchNonTrimmedDOI() throws FetcherException {
+ Optional<BibEntry> fetchedEntry = fetcher.performSearchById("http s://doi.org/ 10.1109 /ICWS .2007.59 ");
+ assertEquals(Optional.of(bibEntryDecker2007), fetchedEntry);
+ }
 }

src/test/java/org/jabref/model/entry/identifier/DOITest.java

@@ -143,4 +143,12 @@ public void findDoiInsideArbitraryText() {
  public void noDOIFoundInsideArbitraryText() {
  assertEquals(Optional.empty(), DOI.findInText("text without 28282 a doi"));
  }
+
+ @Test
+ public void parseDOIWithWhiteSpace() {
+ String doiWithSpace = "https : / / doi.org / 10 .1109 /V LHCC.20 04.20";
+ assertEquals("https://doi.org/10.1109/VLHCC.2004.20", DOI.parse(doiWithSpace).get().getURIAsASCIIString());
+
+ }
+
 }