# Punctuation tokens to remove
,
.
`
-
_
=
?
'
|
"
(
)
{
}
[
]
<
>
*
#
&
^
$
@
!
~
:
;
+
/
\
《
》
—
－
，
。
、
：
；
！
·
？
“
”
）
（
【
】
［
］
●
# the line below contains an IDEOGRAPHIC SPACE character (Used as a space in Chinese)
　

# English Stop Words

   1680; OGHAM SPACE MARK
   2000; EN QUAD
   2001; EM QUAD
   2002; EN SPACE
   2003; EM SPACE
   2004; THREE-PER-EM SPACE
   2005; FOUR-PER-EM SPACE
   2006; SIX-PER-EM SPACE
   2007; FIGURE SPACE
   2008; PUNCTUATION SPACE
   2009; THIN SPACE
   200A; HAIR SPACE
   200B; ZERO WIDTH SPACE
   202F; NARROW NO-BREAK SPACE
   205F; MEDIUM MATHEMATICAL SPACE

# Punctuation tokens to remove
,
.
`
-
_
=
?
'
|
"
(
)
{
}
[
]
<
>
*
#
&
^
$
@
!
~
:
;
+
/
\
《
》
—
－
，
。
、
：
；
！
·
？
“
”
）
（
【
】
［
］
●
# the line below contains an IDEOGRAPHIC SPACE character (Used as a space in Chinese)
　

# English Stop Words

05BF          ; valid                                  # 1.1  HEBREW POINT RAFE
05C0          ; valid                  ;      ; NV8    # 1.1  HEBREW PUNCTUATION PASEQ
05C1..05C2    ; valid                                  # 1.1  HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C3          ; valid                  ;      ; NV8    # 1.1  HEBREW PUNCTUATION SOF PASUQ

    Conscrypt is the bundled security provider on Android so it is not necessary
    to configure it on that platform.

 *  New: `HttpUrl.addQueryParameter()` percent-escapes more characters.
    Previously several ASCII punctuation characters were not percent-escaped
    when used with this method. This does not impact already-encoded query
    parameters in APIs like `HttpUrl.parse()` and
    `HttpUrl.Builder.addEncodedQueryParameter()`.

    // 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

pkg unicode, var Tai_Le *RangeTable
pkg unicode, var Tai_Tham *RangeTable
pkg unicode, var Tai_Viet *RangeTable
pkg unicode, var Tamil *RangeTable
pkg unicode, var Telugu *RangeTable
pkg unicode, var Terminal_Punctuation *RangeTable
pkg unicode, var Thaana *RangeTable
pkg unicode, var Thai *RangeTable
pkg unicode, var Tibetan *RangeTable
pkg unicode, var Tifinagh *RangeTable
pkg unicode, var Title *RangeTable

- Updated command descriptions and examples for grammar and punctuation consistency. ([#103524](https://github.com/kubernetes/kubernetes/pull/103524), [@bergerhoffer](https://github.com/bergerhoffer)) [SIG Auth and CLI]

    *   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`