Improved detection of long DOI's within text (#7260)

* Improved detection of long DOI's within text. fixes #7256. * Fix checkstyle Signed-off-by: Dominik Voigt <Dominik.ingo.voigt@gmail.com> Co-authored-by: Nikolaus Koopmann <nikolauskoopmann@gmail.com>
JabRef · Dec 28, 2020 · 020cc97 · 020cc97
1 parent 27864e9
commit 020cc97
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 1 deletion.
diff --git a/src/main/java/org/jabref/model/entry/identifier/DOI.java b/src/main/java/org/jabref/model/entry/identifier/DOI.java
@@ -45,7 +45,7 @@ public class DOI implements Identifier {
             + "10"                              // directory indicator
             + "(?:\\.[0-9]+)+"                  // registrant codes
             + "[/:]"                            // divider
-            + "(?:[^\\s]+)"                     // suffix alphanumeric without space
+            + "(?:[^\\s,;]+[^,;(\\.\\s)])"      // suffix alphanumeric without " "/","/";" and not ending on "."/","/";"
             + ")";                              // end group \1
 
     // Regex (Short DOI)

diff --git a/src/test/java/org/jabref/model/entry/identifier/DOITest.java b/src/test/java/org/jabref/model/entry/identifier/DOITest.java
@@ -165,12 +165,23 @@ private static Stream<Arguments> testData() {
                 // findDoiInsideArbitraryText
                 Arguments.of("10.1006/jmbi.1998.2354",
                         DOI.findInText("other stuff 10.1006/jmbi.1998.2354 end").get().getDOI()),
+                Arguments.of("10.1007/s10549-018-4743-9",
+                        DOI.findInText("Breast Cancer Res Treat. 2018 July ; 170(1): 77–87. doi:10.1007/s10549-018-4743-9. ").get().getDOI()),
+                Arguments.of("10.1007/s10549-018-4743-9",
+                        DOI.findInText("Breast Cancer Res Treat. 2018 July ; 170(1): 77–87. doi:10.1007/s10549-018-4743-9, ").get().getDOI()),
+                Arguments.of("10.1007/s10549-018-4743-9",
+                        DOI.findInText("Breast Cancer Res Treat. 2018 July ; 170(1): 77–87. doi:10.1007/s10549-018-4743-9;something else").get().getDOI()),
+                Arguments.of("10.1007/s10549-018-4743-9.1234",
+                        DOI.findInText("bla doi:10.1007/s10549-018-4743-9.1234 with . in doi").get().getDOI()),
 
                 // findShortDoiInsideArbitraryText
                 Arguments.of("10/12ab", DOI.findInText("other stuff doi:10/12ab end").get().getDOI()),
                 Arguments.of("10/12ab", DOI.findInText("other stuff /urn:doi:10/12ab end").get().getDOI()),
                 Arguments.of("10%12ab", DOI.findInText("other stuff doi:10%12ab end").get().getDOI()),
                 Arguments.of("10%12ab", DOI.findInText("other stuff /doi:10%12ab end").get().getDOI()),
+                Arguments.of("10%12ab", DOI.findInText("other stuff /doi:10%12ab, end").get().getDOI()),
+                Arguments.of("10%12ab", DOI.findInText("other stuff /doi:10%12ab. end").get().getDOI()),
+                Arguments.of("10%12ab", DOI.findInText("other stuff /doi:10%12ab; end").get().getDOI()),
                 Arguments.of("10/1234", DOI.findInText("10/B(C)/15 \n" +
                         " \n" +
                         "10:51 \n" +