bettr cover one additional citation callout pattern

kermitt2 · Jun 7, 2022 · c83d224 · c83d224
1 parent 81b0da1
commit c83d224
Show file tree

Hide file tree

Showing 2 changed files with 24 additions and 4 deletions.
diff --git a/doc/Introduction.md b/doc/Introduction.md
@@ -67,8 +67,8 @@ Many thanks to:
 
 * Vyacheslav Zholudev (Sum&Substance, formerly at ResearchGate)
 * Achraf Azhar (CCSD)
-* Laurent Romary (Inria)
 * Daniel Ecer (eLife)
+* Laurent Romary (Inria)
 * Vitalii Bezsheiko (PKP)
 * Bryan Newbold (Internet Archive)
 * Christopher Boumenot (Microsoft) in particular for the Windows support
@@ -82,4 +82,4 @@ Many thanks to:
 * The JEP team for their great JVM CPython embedding solution
 * Taku Kudo for CRF++ (not used anymore, but all the same, thanks!)
 * Hervé Déjean and his colleagues from Xerox Research Centre Europe, for xml2pdf
-* and the other contributors: Jakob Fix, Tanti Kristanti, Bryan Newbold, Dmitry Katsubo, Phil Gooch, Romain Loth, Maud Medves, Chris Mattmann, Sujen Shah, Joseph Boyd, Guillaume Muller, ...
+* and the other contributors: @elonzh, Jakob Fix, Tanti Kristanti, Bryan Newbold, Dmitry Katsubo, Phil Gooch, Romain Loth, Maud Medves, Chris Mattmann, Sujen Shah, Joseph Boyd, Guillaume Muller, ...
diff --git a/grobid-core/src/main/java/org/grobid/core/utilities/matching/ReferenceMarkerMatcher.java b/grobid-core/src/main/java/org/grobid/core/utilities/matching/ReferenceMarkerMatcher.java
@@ -7,6 +7,7 @@
 import org.apache.lucene.analysis.standard.ClassicAnalyzer;
 import org.apache.lucene.util.Version;
 import org.grobid.core.data.BibDataSet;
+import org.grobid.core.data.BiblioItem;;
 import org.grobid.core.layout.LayoutToken;
 import org.grobid.core.utilities.LayoutTokensUtil;
 import org.grobid.core.utilities.Pair;
@@ -278,7 +279,7 @@ private List<MatchResult> matchAuthorCitation(String text, List<LayoutToken> ref
             List<BibDataSet> matches = authorMatcher.match(c);
             if (matches.size() == 1) {
                 cntManager.i(ReferenceMarkerMatcherCounters.MATCHED_REF_MARKERS);
-                //System.out.println("MATCHED: " + text + "\n" + c + "\n" + matches.get(0).getRawBib());
+//System.out.println("MATCHED: " + text + "\n" + c + "\n" + matches.get(0).getRawBib());
                 results.add(new MatchResult(c, splitItem, matches.get(0)));
             } else {
                 if (matches.size() != 0) {
@@ -405,14 +406,33 @@ private List<BibDataSet> postFilterMatches(String c, List<BibDataSet> matches) {
             String[] sp = c.trim().split(" ");
             //callouts often include parentheses as seen in https://grobid.readthedocs.io/en/latest/training/fulltext/
             final String author = sp[0].replaceAll("[\\(\\[]", "").toLowerCase();
-
             ArrayList<BibDataSet> bibDataSets = Lists.newArrayList(Iterables.filter(matches, new Predicate<BibDataSet>() {
                 @Override
                 public boolean apply(BibDataSet bibDataSet) {
+                    // first author last name formatted raw bib
                     return bibDataSet.getRawBib().trim().toLowerCase().startsWith(author);
                 }
             }));
 
+            if (bibDataSets.size() == 1) {
+                return bibDataSets;
+            }
+
+            bibDataSets = Lists.newArrayList(Iterables.filter(matches, new Predicate<BibDataSet>() {
+                @Override
+                public boolean apply(BibDataSet bibDataSet) {
+                    BiblioItem resBib = bibDataSet.getResBib();
+                    if (resBib == null)
+                        return false;
+                    String firstAuthorLastName = resBib.getFirstAuthorSurname();
+                    if (firstAuthorLastName == null)
+                        return false;
+                    firstAuthorLastName = firstAuthorLastName.toLowerCase();
+                    // first author forename last name formatted raw bib
+                    return firstAuthorLastName.equals(author);
+                }
+            }));
+
             if (bibDataSets.size() <= 1) {
                 return bibDataSets;
             }