add Cleanup for copying over physcial review article id as the page n… (

#7025) * add Cleanup for copying over physcial review article id as the page number * remove PageFieldCleanup, add private methods to DoiFetcher * remove comment from DoiFetcherTest * replace regex with substring and string comparison * fix checkstyle issues * fix checkstyle issues * add regex to check aps doi format * move suffix pattern to private static field * add changelog entry * add issue link to changelog entry
JabRef · Oct 20, 2020 · a7b05d0 · a7b05d0
1 parent 79f0221
commit a7b05d0
Show file tree

Hide file tree

Showing 3 changed files with 53 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -15,6 +15,8 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 - We added a query parser and mapping layer to enable conversion of queries formulated in simplified lucene syntax by the user into api queries. [#6799](https://github.com/JabRef/jabref/pull/6799)
 - We added some basic functionality to customise the look of JabRef by importing a css theme file. [#5790](https://github.com/JabRef/jabref/issues/5790)
 - We added connection check function in network preference setting [#6560](https://github.com/JabRef/jabref/issues/6560)
+- We added a DOI format and organization check to detect [American Physical Society](https://journals.aps.org/) journals to copy the article ID
+to the page field for cases where the page numbers are missing. [#7019](https://github.com/JabRef/jabref/issues/7019)
 - We added a new fetcher to enable users to search jstor.org [#6627](https://github.com/JabRef/jabref/issues/6627)
 
 ### Changed

diff --git a/src/main/java/org/jabref/logic/importer/fetcher/DoiFetcher.java b/src/main/java/org/jabref/logic/importer/fetcher/DoiFetcher.java
@@ -5,6 +5,7 @@
 import java.util.Collections;
 import java.util.List;
 import java.util.Optional;
+import java.util.regex.Pattern;
 
 import org.jabref.logic.cleanup.FieldFormatterCleanup;
 import org.jabref.logic.formatter.bibtexfields.ClearFormatter;
@@ -22,6 +23,7 @@
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.StandardField;
 import org.jabref.model.entry.identifier.DOI;
+import org.jabref.model.entry.types.StandardEntryType;
 import org.jabref.model.util.DummyFileUpdateMonitor;
 import org.jabref.model.util.OptionalUtil;
 
@@ -32,8 +34,13 @@
 import org.slf4j.LoggerFactory;
 
 public class DoiFetcher implements IdBasedFetcher, EntryBasedFetcher {
+
     public static final String NAME = "DOI";
 
+    private static final String APS_JOURNAL_ORG_DOI_ID = "1103";
+    private static final String APS_SUFFIX = "([\\w]+\\.)([\\w]+\\.)([\\w]+)";
+    private static final Pattern APS_SUFFIX_PATTERN = Pattern.compile(APS_SUFFIX);
+
     private static final Logger LOGGER = LoggerFactory.getLogger(DoiFetcher.class);
 
     private final ImportFormatPreferences preferences;
@@ -75,6 +82,14 @@ public Optional<BibEntry> performSearchById(String identifier) throws FetcherExc
                 fetchedEntry = BibtexParser.singleFromString(bibtexString, preferences, new DummyFileUpdateMonitor());
                 fetchedEntry.ifPresent(this::doPostCleanup);
 
+                // Check if the entry is an APS journal and add the article id as the page count if page field is missing
+                if (fetchedEntry.isPresent() && fetchedEntry.get().hasField(StandardField.DOI)) {
+                    BibEntry entry = fetchedEntry.get();
+                    if (isAPSJournal(entry, entry.getField(StandardField.DOI).get()) && !entry.hasField(StandardField.PAGES)) {
+                        setPageCountToArticleId(entry, entry.getField(StandardField.DOI).get());
+                    }
+                }
+
                 return fetchedEntry;
             } else {
                 throw new FetcherException(Localization.lang("Invalid DOI: '%0'.", identifier));
@@ -123,4 +138,19 @@ public Optional<String> getAgency(DOI doi) throws IOException {
 
         return agency;
     }
+
+    private void setPageCountToArticleId(BibEntry entry, String doiAsString) {
+        String articleId = doiAsString.substring(doiAsString.lastIndexOf('.') + 1);
+        entry.setField(StandardField.PAGES, articleId);
+    }
+
+    // checks if the entry is an APS journal by comparing the organization id and the suffix format
+    private boolean isAPSJournal(BibEntry entry, String doiAsString) {
+        if (!entry.getType().equals(StandardEntryType.Article)) {
+            return false;
+        }
+        String suffix = doiAsString.substring(doiAsString.lastIndexOf('/') + 1);
+        String organizationId = doiAsString.substring(doiAsString.indexOf('.') + 1, doiAsString.indexOf('/'));
+        return organizationId.equals(APS_JOURNAL_ORG_DOI_ID) && APS_SUFFIX_PATTERN.matcher(suffix).matches();
+    }
 }
diff --git a/src/test/java/org/jabref/logic/importer/fetcher/DoiFetcherTest.java b/src/test/java/org/jabref/logic/importer/fetcher/DoiFetcherTest.java
@@ -24,6 +24,7 @@ public class DoiFetcherTest {
     private BibEntry bibEntryBurd2011;
     private BibEntry bibEntryDecker2007;
     private BibEntry bibEntryIannarelli2019;
+    private BibEntry bibEntryStenzel2020;
 
     @BeforeEach
     public void setUp() {
@@ -68,6 +69,20 @@ public void setUp() {
                                                                         .withField(StandardField.JOURNAL, "Chemical Engineering Transactions")
                                                                         .withField(StandardField.PAGES, "871-876")
                                                                         .withField(StandardField.VOLUME, "77");
+        bibEntryStenzel2020 = new BibEntry();
+        bibEntryStenzel2020.setType(StandardEntryType.Article);
+        bibEntryStenzel2020.setCitationKey("Stenzel_2020");
+        bibEntryStenzel2020.setField(StandardField.AUTHOR, "L. Stenzel and A. L. C. Hayward and U. Schollwöck and F. Heidrich-Meisner");
+        bibEntryStenzel2020.setField(StandardField.JOURNAL, "Physical Review A");
+        bibEntryStenzel2020.setField(StandardField.TITLE, "Topological phases in the Fermi-Hofstadter-Hubbard model on hybrid-space ladders");
+        bibEntryStenzel2020.setField(StandardField.YEAR, "2020");
+        bibEntryStenzel2020.setField(StandardField.MONTH, "aug");
+        bibEntryStenzel2020.setField(StandardField.VOLUME, "102");
+        bibEntryStenzel2020.setField(StandardField.DOI, "10.1103/physreva.102.023315");
+        bibEntryStenzel2020.setField(StandardField.PUBLISHER, "American Physical Society ({APS})");
+        bibEntryStenzel2020.setField(StandardField.PAGES, "023315");
+        bibEntryStenzel2020.setField(StandardField.NUMBER, "2");
+
     }
 
     @Test
@@ -108,4 +123,10 @@ public void testPerformSearchNonTrimmedDOI() throws FetcherException {
         Optional<BibEntry> fetchedEntry = fetcher.performSearchById("http s://doi.org/ 10.1109 /ICWS .2007.59 ");
         assertEquals(Optional.of(bibEntryDecker2007), fetchedEntry);
     }
+
+    @Test
+    public void testAPSJournalCopiesArticleIdToPageField() throws FetcherException {
+        Optional<BibEntry> fetchedEntry = fetcher.performSearchById("10.1103/physreva.102.023315");
+        assertEquals(Optional.of(bibEntryStenzel2020), fetchedEntry);
+    }
 }