Added integrity checker to detect HTML encoded characters in fields

CHANGELOG.md

@@ -19,6 +19,7 @@ to [sourceforge feature requests](https://sourceforge.net/p/jabref/features/) by
 - Added integrity checker for an odd number of unescaped '#'
 - Implemented [feature request 384](https://sourceforge.net/p/jabref/features/384): The merge entries dialog now show all text and colored differences between the fields
 - Implemented [#1233](https://github.com/JabRef/jabref/issues/1233): Group side pane now takes up all the remaining space
+- Added integrity check detecting HTML-encoded characters
 
 ### Fixed
 

src/main/java/net/sf/jabref/logic/integrity/IntegrityCheck.java

@@ -62,6 +62,7 @@ private List<IntegrityMessage> checkBibtexEntry(BibEntry entry) {
         result.addAll(new AbbreviationChecker("journal").check(entry));
         result.addAll(new AbbreviationChecker("booktitle").check(entry));
         result.addAll(new BibStringChecker().check(entry));
+        result.addAll(new HTMLCharacterChecker().check(entry));
 
         return result;
     }
@@ -355,4 +356,27 @@ public List<IntegrityMessage> check(BibEntry entry) {
         }
     }
 
+    private static class HTMLCharacterChecker implements Checker {
+
+        // Detect any HTML encoded character,
+        private static final Pattern HTML_CHARACTER_PATTERN = Pattern.compile("&[#\\p{Alnum}]+;");
+
+
+        /**
+         * Checks, if there are any HTML encoded characters in the fields
+         */
+        @Override
+        public List<IntegrityMessage> check(BibEntry entry) {
+            List<IntegrityMessage> results = new ArrayList<>();
+            for (Map.Entry<String, String> field : entry.getFieldMap().entrySet()) {
+                Matcher characterMatcher = HTML_CHARACTER_PATTERN.matcher(field.getValue());
+                if (characterMatcher.find()) {
+                    results.add(new IntegrityMessage(Localization.lang("HTML encoded character found"), entry,
+                            field.getKey()));
+                }
+            }
+            return results;
+        }
+    }
+
 }

src/main/resources/l10n/JabRef_da.properties

@@ -1672,3 +1672,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_de.properties

@@ -2390,3 +2390,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_en.properties

@@ -2254,3 +2254,4 @@ character=character
 word=word
 Show_symmetric_diff=Show_symmetric_diff
 
+HTML_encoded_character_found=HTML_encoded_character_found

src/main/resources/l10n/JabRef_es.properties

@@ -1573,3 +1573,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_fa.properties

@@ -2360,3 +2360,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_fr.properties

@@ -1616,3 +1616,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_in.properties

@@ -1592,3 +1592,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_it.properties

@@ -1692,3 +1692,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_ja.properties

@@ -2336,3 +2336,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_nl.properties

@@ -2370,3 +2370,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_no.properties

@@ -2766,3 +2766,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_pt_BR.properties

@@ -1586,3 +1586,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_ru.properties

@@ -2337,3 +2337,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_sv.properties

@@ -1530,3 +1530,5 @@ character=bokstav
 word=ord
 
 Show_symmetric_diff=Visa_skillnad_symmetriskt
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_tr.properties

@@ -1604,3 +1604,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_vi.properties

@@ -2361,3 +2361,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/main/resources/l10n/JabRef_zh.properties

@@ -1598,3 +1598,5 @@ character=
 word=
 
 Show_symmetric_diff=
+
+HTML_encoded_character_found=

src/test/java/net/sf/jabref/logic/integrity/IntegrityCheckTest.java

@@ -160,6 +160,16 @@ public void testBibStringChecks() {
         assertWrong(createContext("author", "#einstein# #amp; #newton#"));
     }
 
+    @Test
+    public void testHTMLCharacterChecks() {
+        assertCorrect(createContext("title", "Not a single {HTML} character"));
+        assertCorrect(createContext("month", "#jan#"));
+        assertCorrect(createContext("author", "A. Einstein and I. Newton"));
+        assertWrong(createContext("author", "Lenhard, Jörg"));
+        assertWrong(createContext("author", "Lenhard, Jãrg"));
+        assertWrong(createContext("journal", "Ärling Ström for – ‱"));
+    }
+
     private BibDatabaseContext createContext(String field, String value, String type) {
         BibEntry entry = new BibEntry();
         entry.setField(field, value);