// container runtime prefixes, etc.
	regexp.MustCompile(`` +
		// "pod"-prefixed Pod UID (with punctuation separated groups) followed by punctuation
		`[[:punct:]]pod(?P<poduid>[[:xdigit:]]{8}[[:punct:]]?[[:xdigit:]]{4}[[:punct:]]?[[:xdigit:]]{4}[[:punct:]]?[[:xdigit:]]{4}[[:punct:]]?[[:xdigit:]]{12})[[:punct:]]` +
		// zero or more punctuation separated "segments" (e.g. "docker-")

   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

issues:
  exclude-use-default: false
  exclude:
    - "empty-block:"
    - "unused-parameter:"
    - "dot-imports:"
    - should have a package comment

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

// 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.

continue     for          import       return       var
</pre>

<h3 id="Operators_and_punctuation">Operators and punctuation</h3>

<p>
The following character sequences represent <a href="#Operators">operators</a>
(including <a href="#Assignment_statements">assignment operators</a>) and punctuation
[<a href="#Go_1.18">Go 1.18</a>]:
</p>
<pre class="grammar">

package path followed by a period and the symbol name:
<code>fmt.Printf</code> or <code>math/rand.Int</code>.
Because the assembler's parser treats period and slash as punctuation,
those strings cannot be used directly as identifier names.
Instead, the assembler allows the middle dot character U+00B7
and the division slash U+2215 in identifiers and rewrites them to
plain period and slash.

continue     for          import       return       var
</pre>

<h3 id="Operators_and_punctuation">Operators and punctuation</h3>

<p>
The following character sequences represent <a href="#Operators">operators</a>
(including <a href="#Assignments">assignment operators</a>) and punctuation:
</p>
<pre class="grammar">
+    &amp;     +=    &amp;=     &amp;&amp;    ==    !=    (    )

    // 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`