Merge branch 'main' into fix-for-issue-JabRef#12272

Author: oops-shlok

.github/ISSUE_TEMPLATE/suggestion-for-improvement.md

@@ -3,13 +3,14 @@ name: Suggestion for improvement
 about: Suggest an enhancement
 title: ''
 labels: ''
+type: 'feature'
 assignees: ''
 
 ---
 
 <!--
 Please use the GitHub issue tracker only for bug reports and smaller suggestions for improvements.
-Requests for completely new features, questions and general feedback is now handled at http://discourse.jabref.org.
+Requests for completely new features, questions and general feedback is now handled at https://discourse.jabref.org.
 Thanks!
 -->
 

.github/workflows/assign-issue.yml

@@ -19,7 +19,7 @@ jobs:
         uses: takanome-dev/assign-issue-action@fix-rate-limit-err
         with:
           github_token: '${{ secrets.GITHUB_TOKEN }}'
-          days_until_unassign: 90
+          days_until_unassign: 45
           maintainers: 'koppor,Siedlerchr,ThiloteE,calixtus,HoussemNasri,subhramit,LinusDietz'
           assigned_comment: |
             👋 Hey @{{ handle }}, thank you for your interest in this issue! 🎉
@@ -34,8 +34,9 @@ jobs:
 
             ⏳ Please note, you will be automatically unassigned if the issue isn't closed within **{{ total_days }} days** (by **{{ unassigned_date }}**). A maintainer can also add the "**{{ pin_label }}**"" label to prevent automatic unassignment.
       - name: Move Issue to "Assigned" Column in "Candidates for University Projects"
-        if: steps.assign.outputs.assigned == 'yes'
-        uses: m7kvqbe1/github-action-move-issues@feat/skip-if-not-in-project-flag
+        uses: koppor/github-action-move-issues@work-for-labeled
+        # Action currently works for issues only - pre-condition: https://github.com/takanome-dev/assign-issue-action/issues/269 fixed
+        if: github.event_name == 'issue_comment'
         with:
           github-token: ${{ secrets.GH_TOKEN_ACTION_MOVE_ISSUE }}
           project-url: "https://github.com/orgs/JabRef/projects/3"
@@ -45,8 +46,8 @@ jobs:
           default-column: "Free to take"
           skip-if-not-in-project: true
       - name: Move Issue to "Assigned" Column in "Good First Issues"
-        if: steps.assign.outputs.assigned == 'yes'
-        uses: m7kvqbe1/github-action-move-issues@feat/skip-if-not-in-project-flag
+        uses: koppor/github-action-move-issues@work-for-labeled
+        if: github.event_name == 'issue_comment'
         with:
           github-token: ${{ secrets.GH_TOKEN_ACTION_MOVE_ISSUE }}
           project-url: "https://github.com/orgs/JabRef/projects/5"

CHANGELOG.md

@@ -15,6 +15,7 @@ Note that this project **does not** adhere to [Semantic Versioning](https://semv
 - We added a new CLI that supports txt, csv, and console-based output for consistency in BibTeX entries. [#11984](https://github.com/JabRef/jabref/issues/11984)
 - We added a new dialog for bibliography consistency check. [#11950](https://github.com/JabRef/jabref/issues/11950)
 - We added a feature for copying entries to libraries, available via the context menu, with an option to include cross-references. [#12374](https://github.com/JabRef/jabref/pull/12374)
+- We added an integrity check if a URL appears in a title. [#12354](https://github.com/JabRef/jabref/issues/12354)
 
 ### Changed
 
@@ -27,6 +28,7 @@ Note that this project **does not** adhere to [Semantic Versioning](https://semv
 - The "automatically sync bibliography when citing" feature of the LibreOffice integration is now disabled by default (can be enabled in settings). [#12472](https://github.com/JabRef/jabref/pull/12472)
 - For the Citation key generator patterns, we reverted how `[authorsAlpha]` would behave to the original pattern and renamed the LNI-based pattern introduced in V6.0-alpha to `[authorsAlphaLNI]`. [#12499](https://github.com/JabRef/jabref/pull/12499)
 - We keep the list of recent files if one files could not be found. [#12517](https://github.com/JabRef/jabref/pull/12517)
+- During the import process, the labels indicating individual paragraphs within an abstract returned by PubMed/Medline XML are preserved. [#12527](https://github.com/JabRef/jabref/issues/12527)
 
 ### Fixed
 

src/main/java/org/jabref/logic/importer/fileformat/MedlineImporter.java

@@ -15,9 +15,9 @@
 import java.util.Optional;
 
 import javax.xml.stream.XMLInputFactory;
+import javax.xml.stream.XMLStreamConstants;
 import javax.xml.stream.XMLStreamException;
 import javax.xml.stream.XMLStreamReader;
-import javax.xml.stream.events.XMLEvent;
 
 import org.jabref.logic.importer.Importer;
 import org.jabref.logic.importer.ParseException;
@@ -998,7 +998,7 @@ private void addAbstract(XMLStreamReader reader, Map<Field, String> fields, Stri
                             putIfValueNotNull(fields, new UnknownField("copyright"), reader.getText());
                         }
                     }
-                    case "AbstractText" -> handleTextElement(reader, abstractTextList, elementName);
+                    case "AbstractText" -> handleAbstractTextElement(reader, abstractTextList, elementName);
                 }
             }
 
@@ -1008,7 +1008,7 @@ private void addAbstract(XMLStreamReader reader, Map<Field, String> fields, Stri
         }
 
         if (!abstractTextList.isEmpty()) {
-            fields.put(StandardField.ABSTRACT, String.join(" ", abstractTextList));
+            fields.put(StandardField.ABSTRACT, String.join("\n\n", abstractTextList));
         }
     }
 
@@ -1020,7 +1020,25 @@ private void addAbstract(XMLStreamReader reader, Map<Field, String> fields, Stri
     private void handleTextElement(XMLStreamReader reader, List<String> textList, String startElement)
             throws XMLStreamException {
         StringBuilder result = new StringBuilder();
+        handleText(reader, textList, startElement, result);
+    }
+
+    /**
+     * Handles text entities of abstracts that can have inner tags such as {@literal <}i{@literal >}, {@literal <}b{@literal >} etc.
+     * We ignore the tags and return only the characters present in the enclosing parent element.
+     *
+     */
+    private void handleAbstractTextElement(XMLStreamReader reader, List<String> textList, String startElement)
+            throws XMLStreamException {
+        StringBuilder result = new StringBuilder();
+        Optional.ofNullable(reader.getAttributeValue(null, "Label"))
+                .map(String::trim)
+                .filter(label -> !label.isEmpty() && !"UNLABELLED".equals(label))
+                .ifPresent(label -> result.append(label).append(": "));
+        handleText(reader, textList, startElement, result);
+    }
 
+    private void handleText(XMLStreamReader reader, List<String> textList, String startElement, StringBuilder result) throws XMLStreamException {
         while (reader.hasNext()) {
             reader.next();
             if (isStartXMLEvent(reader)) {
@@ -1099,8 +1117,8 @@ private void handleAuthorList(XMLStreamReader reader, Map<Field, String> fields,
             reader.next();
             if (isStartXMLEvent(reader)) {
                 String elementName = reader.getName().getLocalPart();
-                switch (elementName) {
-                    case "Author" -> parseAuthor(reader, authorNames);
+                if ("Author".equals(elementName)) {
+                    parseAuthor(reader, authorNames);
                 }
             }
 
@@ -1121,24 +1139,9 @@ private void parseAuthor(XMLStreamReader reader, List<String> authorNames) throw
             if (isStartXMLEvent(reader)) {
                 String elementName = reader.getName().getLocalPart();
                 switch (elementName) {
-                    case "CollectiveName" -> {
-                        reader.next();
-                        if (isCharacterXMLEvent(reader)) {
-                            collectiveNames.add(reader.getText());
-                        }
-                    }
-                    case "LastName" -> {
-                        reader.next();
-                        if (isCharacterXMLEvent(reader)) {
-                            authorName = new StringBuilder(reader.getText());
-                        }
-                    }
-                    case "ForeName" -> {
-                        reader.next();
-                        if (isCharacterXMLEvent(reader)) {
-                            authorName.append(", ").append(reader.getText());
-                        }
-                    }
+                    case "CollectiveName" -> parseCollectiveName(reader, collectiveNames);
+                    case "LastName" -> authorName = parseLastName(reader, authorName);
+                    case "ForeName" -> parseForeName(reader, authorName);
                 }
             }
 
@@ -1155,6 +1158,28 @@ private void parseAuthor(XMLStreamReader reader, List<String> authorNames) throw
         }
     }
 
+    private void parseForeName(XMLStreamReader reader, StringBuilder authorName) throws XMLStreamException {
+        reader.next();
+        if (isCharacterXMLEvent(reader)) {
+            authorName.append(", ").append(reader.getText());
+        }
+    }
+
+    private StringBuilder parseLastName(XMLStreamReader reader, StringBuilder authorName) throws XMLStreamException {
+        reader.next();
+        if (isCharacterXMLEvent(reader)) {
+            authorName = new StringBuilder(reader.getText());
+        }
+        return authorName;
+    }
+
+    private void parseCollectiveName(XMLStreamReader reader, List<String> collectiveNames) throws XMLStreamException {
+        reader.next();
+        if (isCharacterXMLEvent(reader)) {
+            collectiveNames.add(reader.getText());
+        }
+    }
+
     private void putIfValueNotNull(Map<Field, String> fields, Field field, String value) {
         if (value != null) {
             fields.put(field, value);
@@ -1181,15 +1206,15 @@ private String fixPageRange(String pageRange) {
     }
 
     private boolean isCharacterXMLEvent(XMLStreamReader reader) {
-        return reader.getEventType() == XMLEvent.CHARACTERS;
+        return reader.getEventType() == XMLStreamConstants.CHARACTERS;
     }
 
     private boolean isStartXMLEvent(XMLStreamReader reader) {
-        return reader.getEventType() == XMLEvent.START_ELEMENT;
+        return reader.getEventType() == XMLStreamConstants.START_ELEMENT;
     }
 
     private boolean isEndXMLEvent(XMLStreamReader reader) {
-        return reader.getEventType() == XMLEvent.END_ELEMENT;
+        return reader.getEventType() == XMLStreamConstants.END_ELEMENT;
     }
 
     @Override

src/main/java/org/jabref/logic/integrity/FieldCheckers.java

@@ -48,6 +48,9 @@ private static Multimap<Field, ValueChecker> getAllMap(BibDatabaseContext databa
         fieldCheckers.put(StandardField.KEY, new ValidCitationKeyChecker());
         fieldCheckers.put(InternalField.KEY_FIELD, new ValidCitationKeyChecker());
 
+        fieldCheckers.put(StandardField.TITLE, new NoURLChecker());
+        fieldCheckers.put(StandardField.BOOKTITLE, new NoURLChecker());
+
         if (databaseContext.isBiblatexMode()) {
             fieldCheckers.put(StandardField.DATE, new DateChecker());
             fieldCheckers.put(StandardField.URLDATE, new DateChecker());

src/main/java/org/jabref/logic/integrity/NoURLChecker.java

@@ -0,0 +1,22 @@
+package org.jabref.logic.integrity;
+
+import java.util.Optional;
+
+import org.jabref.logic.l10n.Localization;
+import org.jabref.logic.util.URLUtil;
+import org.jabref.model.strings.StringUtil;
+
+public class NoURLChecker implements ValueChecker {
+
+    public Optional<String> checkValue(String value) {
+        if (StringUtil.isBlank(value)) {
+            return Optional.empty();
+        }
+
+        if (URLUtil.URL_PATTERN.matcher(value).find()) {
+            return Optional.of(Localization.lang("contains a URL"));
+        }
+
+        return Optional.empty();
+    }
+}

src/main/java/org/jabref/logic/util/URLUtil.java

@@ -7,13 +7,22 @@
 import java.net.URLDecoder;
 import java.nio.charset.StandardCharsets;
 import java.util.Objects;
+import java.util.regex.Pattern;
 
 /**
  * URL utilities for URLs in the JabRef logic.
  * <p>
  * For GUI-oriented URL utilities see {@link org.jabref.gui.fieldeditors.URLUtil}.
  */
 public class URLUtil {
+
+    private static final String URL_REGEX = "(?i)\\b((?:https?|ftp)://[^\\s]+)";
+
+    /**
+     * Pattern matches a string containing a URL with a protocol
+     */
+    public static final Pattern URL_PATTERN = Pattern.compile(URL_REGEX, Pattern.CASE_INSENSITIVE);
+
     private static final String URL_EXP = "^(https?|ftp)://.+";
     // Detect Google search URL
     private static final String GOOGLE_SEARCH_EXP = "^https?://(?:www\\.)?google\\.[\\.a-z]+?/url.*";

src/main/resources/l10n/JabRef_en.properties

@@ -1626,16 +1626,18 @@ JabRef\ would\ not\ have\ been\ possible\ without\ the\ help\ of\ our\ contribut
 
 HTML\ encoded\ character\ found=HTML encoded character found
 booktitle\ ends\ with\ 'conference\ on'=booktitle ends with 'conference on'
+contains\ a\ URL=contains a URL
 
 incorrect\ control\ digit=incorrect control digit
 incorrect\ format=incorrect format
+
 Copied\ version\ to\ clipboard=Copied version to clipboard
 
 Citation\ key=Citation key
 Message=Message
 
-
 MathSciNet\ Review=MathSciNet Review
+
 Reset\ all=Reset all
 
 Decryption\ not\ supported.=Decryption not supported.

src/test/java/org/jabref/logic/integrity/NoURLCheckerTest.java

@@ -0,0 +1,30 @@
+package org.jabref.logic.integrity;
+
+import java.util.Optional;
+
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.CsvSource;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertNotEquals;
+
+public class NoURLCheckerTest {
+
+    private final NoURLChecker checker = new NoURLChecker();
+
+    @ParameterizedTest(name = "{index}. Title: \"{0}\"")
+    @CsvSource({
+            "Proceedings of the https://example.com/conference",
+            "Find more at http://mywebsite.org/article",
+            "Visit ftp://files.example.com/download",
+    })
+    void fieldShouldRaiseWarningForFullURLs(String title) {
+        assertNotEquals(Optional.empty(), checker.checkValue(title));
+    }
+
+    @Test
+    void fieldShouldAcceptURLWithoutProtocol() {
+        assertEquals(Optional.empty(), checker.checkValue("Applying Trip@dvice Recommendation Technology to www.visiteurope.com"));
+    }
+}

src/test/resources/org/jabref/logic/importer/fileformat/MedlineImporterTestNbib.bib

@@ -1,5 +1,7 @@
 @article{,
-  abstract = {Just a dummy text. And another dummy},
+  abstract = {BACKGROUND: Just a dummy text.
+
+And another dummy},
   affiliation = {Vanderbilt U, Nashville, TN},
   author = {Gibb, F W and Zamm itt, NaN and Beckett, G and Strachan, M W J},
   chemicals = {Iodine Radioisotopes, Thyroxine},

src/test/resources/org/jabref/logic/importer/fileformat/MedlineImporterTestNbib.xml

@@ -261,7 +261,7 @@
         <PublicationType UI="D016454">Review</PublicationType>
         <PublicationType UI="D017065">Practice Guideline</PublicationType>
         <Abstract>
-            <AbstractText>just a dummy.</AbstractText>
+            <AbstractText Label="UNLABELLED">just a dummy.</AbstractText>
             <CopyrightInformation>Copyright from somwhere</CopyrightInformation>
         </Abstract>
         <Sections>
@@ -369,4 +369,4 @@
     </PubmedBookData>
 </PubmedBookArticle>
 
-</PubmedArticleSet>
+</PubmedArticleSet>