}

    public void test_generateId_specialCharacters() {
        // Test characters that need special encoding
        String input1 = "http://example.com/文档"; // Unicode characters
        String result1 = crawlingInfoHelper.generateId(input1);
        assertNotNull(result1);
        assertEquals(128, result1.length());

        String input2 = "http://example.com/path with spaces";

 * either {@link Character} or {@link Arrays}.
 *
 * <p>All the operations in this class treat {@code char} values strictly numerically; they are
 * neither Unicode-aware nor locale-dependent.
 *
 * <p>See the Guava User Guide article on <a
 * href="https://github.com/google/guava/wiki/PrimitivesExplained">primitive utilities</a>.
 *
 * @author Kevin Bourrillion
 * @since 1.0
 */

        // Special characters in rule ID
        testRule.setRuleId("rule-id_with.special@chars#123");
        assertEquals("rule-id_with.special@chars#123", testRule.getRuleId());

        // Unicode characters
        testRule.setRuleId("ルール日本語");
        assertEquals("ルール日本語", testRule.getRuleId());

        // Whitespace
        testRule.setRuleId("  rule with spaces  ");

            capabilities |= CAP_EXTENDED_SECURITY; // & doesn't copy high bit
        }

        if ((capabilities & SmbConstants.CAP_UNICODE) == 0) {
            // server doesn't want unicode
            if (FORCE_UNICODE) {
                capabilities |= SmbConstants.CAP_UNICODE;
            } else {
                useUnicode = false;
                flags2 &= 0xFFFF ^ SmbConstants.FLAGS2_UNICODE;

// license that can be found in the LICENSE file.

package zip

import (
	"bufio"
	"encoding/binary"
	"errors"
	"hash"
	"hash/crc32"
	"io"
	"io/fs"
	"strings"
	"unicode/utf8"
)

var (
	errLongName  = errors.New("zip: FileHeader.Name too long")
	errLongExtra = errors.New("zip: FileHeader.Extra too long")
)

// Writer implements a zip file writer.
type Writer struct {

# 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

 * either {@link Character} or {@link Arrays}.
 *
 * <p>All the operations in this class treat {@code char} values strictly numerically; they are
 * neither Unicode-aware nor locale-dependent.
 *
 * <p>See the Guava User Guide article on <a
 * href="https://github.com/google/guava/wiki/PrimitivesExplained">primitive utilities</a>.
 *
 * @author Kevin Bourrillion
 * @since 1.0
 */

// license that can be found in the LICENSE file.

package bytes_test

import (
	. "bytes"
	"fmt"
	"internal/testenv"
	"io"
	"math/rand"
	"strconv"
	"testing"
	"unicode/utf8"
)

const N = 10000       // make this bigger for a larger (and slower) test
var testString string // test data for write tests
var testBytes []byte  // test data; same as testString but as a slice.

// along with this program.  If not, see <http://www.gnu.org/licenses/>.

package cmd

import (
	"bytes"
	"context"
	"errors"
	"fmt"
	"maps"
	"path"
	"strings"
	"sync"
	"time"
	"unicode/utf8"

	jsoniter "github.com/json-iterator/go"
	"github.com/minio/madmin-go/v3"
	"github.com/minio/minio/internal/config"
	xioutil "github.com/minio/minio/internal/ioutil"
	"github.com/minio/minio/internal/kms"

        ops. Amongst other things, this Op adds the ability to encode, decode,
        and transcode a variety of input text encoding formats into the main
        Unicode encodings (UTF-8, UTF-16-BE, UTF-32-BE)
    *   Add "unit" attribute to the substr op, which allows obtaining the
        substring of a string containing unicode characters.
    *   Broadcasting support for Ragged Tensors.