Update README and tests for unicodeWordBoundaries feature

Author: JasonPierce

README.md

@@ -88,6 +88,23 @@ profanity.exists('Arsenic is poisonous but not profane');
 // true (matched on arse)
 ```
 
+### unicodeWordBoundaries
+
+Controls whether word boundaries are Unicode-aware. By default this is set to `false` due to the performance impact. 
+
+- When `false` (default), whole-word matching uses ASCII-style boundaries (similar to `\b`) plus underscore `_` as a separator. This is fastest and ideal for ASCII inputs.
+- When `true`, whole-word matching uses Unicode-aware boundaries so words with diacritics (e.g., `vehículo`, `horário`) and compound separators are handled correctly.
+
+```JavaScript
+const profanity = new Profanity({ 
+  unicodeWordBoundaries: true,
+  wholeWord: true, // must be true for boundaries to work
+});
+
+profanity.exists('vehículo horario');
+// false (does not match on "culo" inside "vehículo")
+```
+
 #### Compound Words  
 Profanity detection works on parts of compound words, rather than treating hyphenated or underscore-separated words as indivisible.
 
@@ -135,21 +152,6 @@ profanity.censor('I like big butts and I cannot lie', CensorType.AllVowels);
 // I like big b$tts and I cannot lie
 ```
 
-### unicodeWordBoundaries
-
-Controls whether word boundaries are Unicode-aware. By default this is set to `false` due to the performance impact.
-
-- When `false` (default), whole-word matching uses ASCII-style boundaries (similar to `\b`) plus underscore `_` as a separator. This is fastest and ideal for ASCII inputs.
-- When `true`, whole-word matching uses Unicode-aware boundaries so words with diacritics (e.g., `vehículo`, `horário`) and compound separators are handled correctly.
-
-```JavaScript
-// Enable Unicode-aware boundaries when processing non-ASCII input
-const profanity = new Profanity({ unicodeWordBoundaries: true });
-
-profanity.exists('vehículo horario');
-// false (does not match on "culo" inside "vehículo")
-```
-
 ## Customize the word list
 
 Add words:

tests/profanity-unicode-boundaries.spec.ts

@@ -47,3 +47,36 @@ describe("Unicode word boundaries (wholeWord=true)", () => {
     expect(profanity.exists("véhicule")).to.be.false;
   });
 });
+
+describe("Unicode option interaction with wholeWord=false", () => {
+  it("should detect substrings regardless of unicodeWordBoundaries (es)", () => {
+    const input = "vehículo";
+    const pAscii = new Profanity({ languages: ["es"], wholeWord: false, grawlix: "*****", unicodeWordBoundaries: false });
+    const pUnicode = new Profanity({ languages: ["es"], wholeWord: false, grawlix: "*****", unicodeWordBoundaries: true });
+    expect(pAscii.exists(input)).to.be.true;
+    expect(pAscii.censor(input)).to.equal("vehí*****");
+    expect(pUnicode.exists(input)).to.be.true;
+    expect(pUnicode.censor(input)).to.equal("vehí*****");
+  });
+
+  it("should detect substrings regardless of unicodeWordBoundaries (fr)", () => {
+    const input = "véhicule";
+    const pAscii = new Profanity({ languages: ["fr"], wholeWord: false, unicodeWordBoundaries: false });
+    const pUnicode = new Profanity({ languages: ["fr"], wholeWord: false, unicodeWordBoundaries: true });
+    expect(pAscii.exists(input)).to.be.true; // matches 'cul'
+    expect(pUnicode.exists(input)).to.be.true; // matches 'cul'
+  });
+});
+
+describe("Unicode off with wholeWord=true (legacy ASCII boundaries)", () => {
+  it("should match 'culo' inside 'vehículo' when unicodeWordBoundaries=false", () => {
+    const profanity = new Profanity({ languages: ["es"], wholeWord: true, grawlix: "*****", unicodeWordBoundaries: false });
+    expect(profanity.exists("vehículo")).to.be.true;
+    expect(profanity.censor("vehículo")).to.equal("vehí*****");
+  });
+
+  it("should not match 'cul' inside 'véhicule' even when unicodeWordBoundaries=false", () => {
+    const profanity = new Profanity({ languages: ["fr"], wholeWord: true, unicodeWordBoundaries: false });
+    expect(profanity.exists("véhicule")).to.be.false;
+  });
+});