Handle case of Medline journal data missing parenthesis

eclipse-pass · Jan 19, 2024 · c025bb4 · c025bb4
1 parent 0c6a2e7
commit c025bb4
Show file tree

Hide file tree

Showing 3 changed files with 22 additions and 4 deletions.
diff --git a/...s-journal-loader-nih/src/main/java/org/eclipse/pass/loader/journal/nih/MedlineReader.java b/...s-journal-loader-nih/src/main/java/org/eclipse/pass/loader/journal/nih/MedlineReader.java
@@ -82,7 +82,8 @@ private Journal read(BufferedReader reader) {
                     } else if (line.startsWith(ISSN_FIELD)) {
                         final String issn = extract(line);
                         final String type = extractType(line);
-                        if (issn.length() > 0) {
+
+                        if (issn.length() > 0 && type != null) {
                             j.getIssns().add(String.join(":", type, issn));
                         }
                     } else if (line.startsWith(ABBR_FIELD)) {
@@ -104,7 +105,14 @@ private String extract(String line) {
     }
 
     private String extractType(String line) {
-        return line.substring(line.indexOf("(") + 1, line.indexOf(")")).trim();
+        int open = line.indexOf("(");
+        int close = line.indexOf(")");
+
+        if (open == -1 || close == -1) {
+            return null;
+        }
+
+        return line.substring(open + 1, close).trim();
     }
 
     @Override

diff --git a/...urnal-loader-nih/src/test/java/org/eclipse/pass/loader/journal/nih/MedlineReaderTest.java b/...urnal-loader-nih/src/test/java/org/eclipse/pass/loader/journal/nih/MedlineReaderTest.java
@@ -41,11 +41,12 @@ public void medlineIssnTest() throws Exception {
 
             final List<Journal> records = toTest.readJournals(in, UTF_8).collect(Collectors.toList());
 
-            assertEquals(3, records.size());
+            assertEquals(4, records.size());
 
             assertEquals(records.get(0).getIssns(), Collections.singletonList("Print:0000-0001"));
             assertEquals(records.get(1).getIssns(), Collections.singletonList("Online:0000-0002"));
             assertEquals(records.get(2).getIssns(), Arrays.asList("Print:0000-0003", "Online:0000-0004"));
+            assertEquals(records.get(3).getIssns(), Collections.EMPTY_LIST);
         }
     }
 
@@ -57,15 +58,17 @@ public void medlineTitlesAndAbbreviationsTest() throws Exception {
 
             final List<Journal> records = toTest.readJournals(in, UTF_8).collect(Collectors.toList());
 
-            assertEquals(3, records.size());
+            assertEquals(4, records.size());
 
             assertEquals("First Journal", records.get(0).getJournalName());
             assertEquals("Second Journal", records.get(1).getJournalName());
             assertEquals("Third Journal", records.get(2).getJournalName());
+            assertEquals("Fourth Journal", records.get(3).getJournalName());
 
             assertEquals("1jr", records.get(0).getNlmta());
             assertEquals("2jr", records.get(1).getNlmta());
             assertEquals("3jr", records.get(2).getNlmta());
+            assertEquals("4jr", records.get(3).getNlmta());
         }
     }
 

diff --git a/pass-journal-loader/pass-journal-loader-nih/src/test/resources/medline.txt b/pass-journal-loader/pass-journal-loader-nih/src/test/resources/medline.txt
@@ -23,3 +23,10 @@ ISSN (Online): 0000-0004
 IsoAbbr: 3jr
 NlmId: abc1232
 --------------------------------------------------------
+JrId: 4
+JournalTitle: Fourth Journal
+MedAbbr: 4jr
+ISSN: 0000-0005
+IsoAbbr: 3jr
+NlmId: abc1233
+--------------------------------------------------------