Improved getArxivId Implementation

JabRef · Jan 1, 2025 · 457bb3f · 457bb3f
1 parent 06b6bb0
commit 457bb3f
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 5 deletions.
diff --git a/src/main/java/org/jabref/logic/importer/fileformat/PdfContentImporter.java b/src/main/java/org/jabref/logic/importer/fileformat/PdfContentImporter.java
@@ -370,8 +370,6 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
         String publisher = null;
 
         EntryType type = StandardEntryType.InProceedings;
-        // sometimes ArXiv ID is read before all parameters
-        getArXivId(null);
         if (curString.length() > 4) {
             // special case: possibly conference as first line on the page
             extractYear();
@@ -392,6 +390,8 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
                 }
             }
         }
+        // sometimes ArXiv ID is read before title
+        getArXivId(null);
         // start: title
         fillCurStringWithNonEmptyLines();
         title = streamlineTitle(curString);
@@ -609,11 +609,15 @@ private String getDoi(String doi) {
 
     private String getArXivId(String arXivId) {
         if (arXivId == null) {
-            arXivId = ArXivIdentifier.parse(curString).map(ArXivIdentifier::asString).orElse(null);
+            String arXiv = curString.split(" ")[0];
+            arXivId = ArXivIdentifier.parse(arXiv).map(ArXivIdentifier::asString).orElse(null);
             if (arXivId != null) {
                 if (curString.length() > arXivId.length() + 7) {
+                    // The arxiv string also contains the year
                     curString = curString.substring(arXivId.length() + 7);
                     extractYear();
+                    curString = "";
+                    proceedToNextNonEmptyLine();
                 }
                 return arXivId;
             }

diff --git a/src/main/java/org/jabref/model/entry/identifier/ArXivIdentifier.java b/src/main/java/org/jabref/model/entry/identifier/ArXivIdentifier.java
@@ -38,7 +38,7 @@ public class ArXivIdentifier extends EprintIdentifier {
     }
 
     public static Optional<ArXivIdentifier> parse(String value) {
-        String identifier = value.split(" ")[0];
+        String identifier = value.replace(" ", "");
         Pattern identifierPattern = Pattern.compile("(" + ARXIV_PREFIX + ")?\\s?:?\\s?(?<id>\\d{4}\\.\\d{4,5})(v(?<version>\\d+))?\\s?(\\[(?<classification>\\S+)\\])?");
         Matcher identifierMatcher = identifierPattern.matcher(identifier);
         if (identifierMatcher.matches()) {

diff --git a/src/test/java/org/jabref/logic/importer/fileformat/PdfContentImporterTest.java b/src/test/java/org/jabref/logic/importer/fileformat/PdfContentImporterTest.java
@@ -133,7 +133,7 @@ British Journal of Nutrition (2008), 99, 1–11 doi: 10.1017/S0007114507795296
     void extractArXivFromPage1() {
         BibEntry entry = new BibEntry(StandardEntryType.TechReport)
                 .withField(StandardField.AUTHOR, "Filippo Riccaa and Alessandro Marchettob and Andrea Stoccoc")
-                .withField(StandardField.TITLE, "[cs.SE] 12 Aug 2024 A Multi-Year Grey Literature Review on AI-assisted Test Automation")
+                .withField(StandardField.TITLE, "A Multi-Year Grey Literature Review on AI-assisted Test Automation")
                 .withField(StandardField.YEAR, "2024")
                 .withField(StandardField.EPRINT, "2408.06224v1")
                 .withField((StandardField.KEYWORDS), "Test Automation Artificial Intelligence AI-assisted Test Automation Grey Literature Automated Test Generation Self-Healing Test Scripts");