assertEquals("WORD" + i, ((TestAnalyzeToken) tokens.get(i)).getReading());
        }
    }

    @Test
    public void testAnalyzeWithPunctuation() {
        // Test analyze with various punctuation
        String text = "Hello, world! How are you? I'm fine.";
        String field = "content";
        String lang = "en";

        List<AnalyzeToken> tokens = analyzer.analyze(text, field, lang);

// Title treats s as UTF-8-encoded bytes and returns a copy with all Unicode letters that begin
// words mapped to their title case.
//
// Deprecated: The rule Title uses for word boundaries does not handle Unicode
// punctuation properly. Use golang.org/x/text/cases instead.
func Title(s []byte) []byte {
	// Use a closure here to remember state.
	// Hackish but effective. Depends on Map scanning in order and calling
	// the closure once per rune.

    // six-per-em space
    assertThat(parse("http://h/\u2006").encodedPath).isEqualTo("/%E2%80%86")
    // figure space
    assertThat(parse("http://h/\u2007").encodedPath).isEqualTo("/%E2%80%87")
    // punctuation space
    assertThat(parse("http://h/\u2008").encodedPath).isEqualTo("/%E2%80%88")
    // thin space
    assertThat(parse("http://h/\u2009").encodedPath).isEqualTo("/%E2%80%89")
    // hair space

    *   Added additional `standardize` and `split` modes to `TextVectorization`:
        *   `standardize="lower"` will lowercase inputs.
        *   `standardize="string_punctuation"` will remove all punctuation.
        *   `split="character"` will split on every unicode character.
    *   Added an `output_mode` argument to the `Discretization` and `Hashing`
        layers with the same semantics as other preprocessing layers. All