Add #12810: Implement escaping for keyword separators (FKA #12888)

CHANGELOG.md

@@ -11,6 +11,7 @@ Note that this project **does not** adhere to [Semantic Versioning](https://semv
 
 ### Added
 
+- We implemented escaping characters `\ ,` when parsing KeywordLists [#12810](https://github.com/JabRef/jabref/issues/12810)
 - We added automatic lookup of DOI at citation information. [#13561](https://github.com/JabRef/jabref/issues/13561)
 - We added a field for the citation count field on the General tab. [#13477](https://github.com/JabRef/jabref/issues/13477)
 - We added automatic lookup of DOI at citation relations [#13234](https://github.com/JabRef/jabref/issues/13234)

jablib/src/main/java/org/jabref/model/entry/KeywordList.java

@@ -8,7 +8,6 @@
 import java.util.List;
 import java.util.Objects;
 import java.util.Set;
-import java.util.StringTokenizer;
 import java.util.stream.Collectors;
 import java.util.stream.Stream;
 
@@ -52,13 +51,37 @@ public static KeywordList parse(String keywordString, Character delimiter, Chara
         Objects.requireNonNull(hierarchicalDelimiter);
 
         KeywordList keywordList = new KeywordList();
+        List<String> hierarchy = new ArrayList<>();
+        StringBuilder currentToken = new StringBuilder();
+        boolean isEscaping = false;
+
+        for (int i = 0; i < keywordString.length(); i++) {
+            char currentChar = keywordString.charAt(i);
+
+            if (isEscaping) {
+                currentToken.append(currentChar);
+                isEscaping = false;
+            } else if (currentChar == '\\') {
+                isEscaping = true;
+            } else if (currentChar == hierarchicalDelimiter) {
+                hierarchy.add(currentToken.toString().trim());
+                currentToken.setLength(0);
+            } else if (currentChar == delimiter) {
+                hierarchy.add(currentToken.toString().trim());
+                currentToken.setLength(0);
+                keywordList.add(Keyword.of(hierarchy.toArray(new String[0])));
+                hierarchy.clear();
+            } else {
+                currentToken.append(currentChar);
+            }
+        }
 
-        StringTokenizer tok = new StringTokenizer(keywordString, delimiter.toString());
-        while (tok.hasMoreTokens()) {
-            String chain = tok.nextToken();
-            Keyword chainRoot = Keyword.of(chain.split(hierarchicalDelimiter.toString()));
-            keywordList.add(chainRoot);
+        // Handle the final token
+        if (!currentToken.isEmpty() || !hierarchy.isEmpty()) {
+            hierarchy.add(currentToken.toString().trim());
+            keywordList.add(Keyword.of(hierarchy.toArray(new String[0])));
         }
+
         return keywordList;
     }
 

jablib/src/test/java/org/jabref/model/entry/KeywordListTest.java

@@ -1,7 +1,13 @@
 package org.jabref.model.entry;
 
+import java.util.stream.Stream;
+
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
+import org.junit.jupiter.params.provider.ValueSource;
 
 import static org.junit.jupiter.api.Assertions.assertEquals;
 
@@ -16,6 +22,17 @@ void setUp() {
         keywords.add("keywordTwo");
     }
 
+    private static Stream<Arguments> provideParseKeywordCases() {
+        return Stream.of(
+                Arguments.of("keyword\\,one, keywordTwo", new KeywordList("keyword,one", "keywordTwo")),
+                Arguments.of("keywordOne\\,, keywordTwo", new KeywordList("keywordOne,", "keywordTwo")),
+                Arguments.of("keyword\\\\, keywordTwo", new KeywordList("keyword\\", "keywordTwo")),
+                Arguments.of("keyword\\,one > sub", new KeywordList(Keyword.of("keyword,one", "sub"))),
+                Arguments.of("one\\,two\\,three, four", new KeywordList("one,two,three", "four")),
+                Arguments.of("keywordOne\\\\", new KeywordList("keywordOne\\"))
+        );
+    }
+
     @Test
     void parseEmptyStringReturnsEmptyList() {
         assertEquals(new KeywordList(), KeywordList.parse("", ','));
@@ -115,4 +132,23 @@ void mergeTwoDistinctKeywordsShouldReturnTheTwoKeywordsMerged() {
     void mergeTwoListsOfKeywordsShouldReturnTheKeywordsMerged() {
         assertEquals(new KeywordList("Figma", "Adobe", "JabRef", "Eclipse", "JetBrains"), KeywordList.merge("Figma, Adobe, JetBrains, Eclipse", "Adobe, JabRef", ','));
     }
+
+    @ParameterizedTest
+    @MethodSource("provideParseKeywordCases")
+    void parseKeywordWithEscapedDelimiterDoesNotSplitKeyword(String input, KeywordList expected) {
+        assertEquals(expected, KeywordList.parse(input, ',', '>'));
+    }
+
+    @ParameterizedTest
+    @ValueSource(strings = {
+            "Keyword > Keyword",
+            "Keyword \\> Keyword"
+    })
+    void roundTripPreservesStructure(String original) {
+        KeywordList parsed = KeywordList.parse(original, ',', '>');
+        String serialized = parsed.toString();
+        KeywordList reparsed = KeywordList.parse(serialized, ',', '>');
+
+        assertEquals(parsed.toString(), reparsed.toString());
+    }
 }

jablib/src/test/java/org/jabref/model/entry/KeywordTest.java

@@ -4,6 +4,8 @@
 import java.util.Set;
 
 import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.ValueSource;
 
 import static org.junit.jupiter.api.Assertions.assertEquals;
 
@@ -25,4 +27,15 @@ void getAllSubchainsAsStringForSimpleChain() {
 
         assertEquals(expected, keywordChain.getAllSubchainsAsString('>'));
     }
+
+    @ParameterizedTest
+    @ValueSource(strings = {
+            "Keyword > Keyword",
+            "Keyword \\> Keyword"
+    })
+    void getSubchainAsString(String input) {
+        Keyword keyword = new Keyword(input);
+        String result = keyword.toString();
+        assertEquals(input, result);
+    }
 }