Fixes #7660 (#7663)

1. Run EprintCleanup on a copy of the entry the ArXiv fetcher is fetching before getting arXiv id from the eprint field;
2. Add two test method. One finds full text with title containing colon and journal, while another finds full text with title containing colon and url.

CHANGELOG.md

@@ -80,6 +80,7 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 - We fixed an issue with opacity of disabled icon-buttons [#7195](https://github.com/JabRef/jabref/issues/7195)
 - We fixed an issue where journal abbreviations in UTF-8 were not recognized [#5850](https://github.com/JabRef/jabref/issues/5850)
 - We fixed an issue where the article title with curly brackets fails to download the arXiv link (pdf file). [#7633](https://github.com/JabRef/jabref/issues/7633)
+- We fixed an issue where the article title with colon fails to download the arXiv link (pdf file). [#7660](https://github.com/JabRef/issues/7660)
 
 ### Removed
 

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

@@ -16,6 +16,8 @@
 import javax.xml.parsers.DocumentBuilderFactory;
 import javax.xml.parsers.ParserConfigurationException;
 
+import org.jabref.logic.cleanup.CleanupJob;
+import org.jabref.logic.cleanup.EprintCleanup;
 import org.jabref.logic.help.HelpFile;
 import org.jabref.logic.importer.FetcherException;
 import org.jabref.logic.importer.FulltextFetcher;
@@ -116,6 +118,9 @@ private Optional<ArXivEntry> searchForEntryById(String id) throws FetcherExcepti
     }
 
     private List<ArXivEntry> searchForEntries(BibEntry entry) throws FetcherException {
+        entry = (BibEntry) entry.clone();
+        CleanupJob cleanupJob = new EprintCleanup();
+        cleanupJob.cleanup(entry);
         // 1. Eprint
         Optional<String> identifier = entry.getField(StandardField.EPRINT);
         if (StringUtil.isNotBlank(identifier)) {

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

@@ -102,6 +102,22 @@ void findFullTextByTitleWithCurlyBracket() throws IOException {
         assertEquals(Optional.of(new URL("https://arxiv.org/pdf/2010.15942v2")), fetcher.findFullText(entry));
     }
 
+    @Test
+    void findFullTextByTitleWithColonAndJournalWithoutEprint() throws IOException {
+        entry.setField(StandardField.TITLE, "Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example");
+        entry.setField(StandardField.JOURNAL, "arXiv:2002.10248v4 [cs]");
+
+        assertEquals(Optional.of(new URL("http://arxiv.org/pdf/2002.10248v4")), fetcher.findFullText(entry));
+    }
+
+    @Test
+    void findFullTextByTitleWithColonAndUrlWithoutEprint() throws IOException {
+        entry.setField(StandardField.TITLE, "Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example");
+        entry.setField(StandardField.URL, "http://arxiv.org/abs/2002.10248v4");
+
+        assertEquals(Optional.of(new URL("http://arxiv.org/pdf/2002.10248v4")), fetcher.findFullText(entry));
+    }
+
     @Test
     void findFullTextByTitleAndPartOfAuthor() throws IOException {
         entry.setField(StandardField.TITLE, "Pause Point Spectra in DNA Constant-Force Unzipping");