benchBytes(b, indexSizes, bmIndexRuneUnicode(unicode.Latin, 'é'))
	})
	b.Run("Cyrillic", func(b *testing.B) {
		// Cyrillic is mostly 2 and 3 byte runes.
		benchBytes(b, indexSizes, bmIndexRuneUnicode(unicode.Cyrillic, 'Ꙁ'))
	})
	b.Run("Han", func(b *testing.B) {
		// Han consists only of 3 and 4 byte runes.
		benchBytes(b, indexSizes, bmIndexRuneUnicode(unicode.Han, '𠀿'))
	})
}

  integrity sha512-h5PpgXkWitc38BBMYawTYMWJHFZJVnBquFE57xFpjB8pJFiF6gZ+bU+WyI/yqXiFR5mdLsgYNaPe8uao6Uv9Og==
  dependencies:
    isobject "^3.0.1"

is-unicode-supported@^0.1.0:
  version "0.1.0"
  resolved "https://registry.yarnpkg.com/is-unicode-supported/-/is-unicode-supported-0.1.0.tgz#3f26c76a809593b52bfa2ecb5710ed2779b522a7"
  integrity sha512-knxG2q4UC3u8stRGyAVJCOdxFmv5DZiRcdlIaAQXAbSfJya+OhopNotLQrstBhququ4ZpuKbDc/8S6mgXgPFPw==

 * example, the Unicode trademark sign (™) could be confused for the letters "TM" in
 * `http://ho™ail.com`. To mitigate this, the single character (™) maps to the string (tm). There
 * is similar policy for all of the 1.1 million Unicode code points. Note that some code points such
 * as "\ud83c\udf69" are not mapped and cannot be used in a hostname.
 *

      .isEqualTo("http://a$dotA126/")
    assertInvalid("http://aa$dotA126/", "Invalid URL host: \"aa$dotA126\"")
  }

  /**
   * UTS 46 Validity Criteria: Decoded punycode must be NFC.
   *
   * https://www.unicode.org/reports/tr46/#Validity_Criteria
   */
  @Test
  fun hostnameInPunycodeNfcAndNfd() {
    // café can be NFC (é is one code point) or NFD (e plus ´ as two code points).

# Whether to remove duplicate terms in documents.
crawler.document.duplicate.term.removed=false
# Unicode space characters for document parsing.
crawler.document.space.chars=u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6
# Unicode full stop characters for document parsing.
crawler.document.fullstop.chars=u002eu06d4u2e3cu3002

        // The actual implementation reassigns _dst = _dst.deferred inside encode(), so we can't verify the exact buffer
        verify(objAttr.root_directory).encode(any(NdrBuffer.class));
        verify(objAttr.object_name).encode(any(NdrBuffer.class));
        verify(objAttr.security_quality_of_service).encode(any(NdrBuffer.class));
    }

    @Test

package bufio_test

import (
	. "bufio"
	"bytes"
	"errors"
	"fmt"
	"internal/asan"
	"io"
	"math/rand"
	"strconv"
	"strings"
	"testing"
	"testing/iotest"
	"time"
	"unicode/utf8"
)

// Reads from a reader and rot13s the result.
type rot13Reader struct {
	r io.Reader
}

func newRot13Reader(r io.Reader) *rot13Reader {
	r13 := new(rot13Reader)
	r13.r = r
	return r13
}

package cmd

import (
	"bytes"
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"maps"
	"net/http"
	"os"
	"slices"
	"sort"
	"strconv"
	"strings"
	"time"
	"unicode/utf8"

	"github.com/klauspost/compress/zip"
	"github.com/minio/madmin-go/v3"
	"github.com/minio/minio/internal/auth"
	"github.com/minio/minio/internal/config/dns"
	"github.com/minio/minio/internal/logger"

	v := BaseOptions{}
	var buf bytes.Buffer
	msgp.Encode(&buf, &v)

	m := v.Msgsize()
	if buf.Len() > m {
		t.Log("WARNING: TestEncodeDecodeBaseOptions Msgsize() is inaccurate")
	}

	vn := BaseOptions{}
	err := msgp.Decode(&buf, &vn)
	if err != nil {
		t.Error(err)
	}

	buf.Reset()
	msgp.Encode(&buf, &v)
	err = msgp.NewReader(&buf).Skip()
	if err != nil {
		t.Error(err)
	}

            //  smb/ftp->http
            // encode
            final StringBuilder buf = new StringBuilder(url.length() + 100);
            for (final char c : url.toCharArray()) {
                if (CharUtil.isUrlChar(c)) {
                    buf.append(c);
                } else {
                    try {
                        buf.append(URLEncoder.encode(String.valueOf(c), urlLinkEncoding));