<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="encodingHelper" class="org.codelibs.fess.crawler.helper.EncodingHelper">
		<postConstruct name="addEncodingMapping">
			<arg>"unicode"</arg>
			<arg>"UTF-16LE"</arg>
		</postConstruct>
	</component>

        // Test toString with buffer containing non-printable characters or special unicode
        String unicodeChars = "你好世界"; // "Hello World" in Chinese
        UnicodeString unicodeStringChinese = new UnicodeString(unicodeChars, false);
        assertEquals(unicodeChars, unicodeStringChinese.toString(), "toString should handle unicode characters correctly");

		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'))
	})
}

//
// You should have received a copy of the GNU Affero General Public License
// along with this program.  If not, see <http://www.gnu.org/licenses/>.

package replication

import (
	"encoding/xml"
	"unicode/utf8"
)

// Tag - a tag for a replication configuration Rule filter.
type Tag struct {
	XMLName xml.Name `xml:"Tag" json:"Tag"`
	Key     string   `xml:"Key,omitempty" json:"Key,omitempty"`

// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package bufio

// Exported for testing only.
import (
	"unicode/utf8"
)

var IsSpace = isSpace

const DefaultBufSize = defaultBufSize

func (s *Scanner) MaxTokenSize(n int) {
	if n < utf8.UTFMax || n > 1e9 {
		panic("bad max token size")
	}
	if n < len(s.buf) {

     */
    int FLAGS2_PERMIT_READ_IF_EXECUTE_PERM = 0x2000;
    /**
     * Use 32-bit status codes flag.
     */
    int FLAGS2_STATUS32 = 0x4000;
    /**
     * Strings are Unicode flag.
     */
    int FLAGS2_UNICODE = 0x8000;

    /**
     * No capabilities.
     */
    int CAP_NONE = 0x0000;
    /**
     * Raw mode transfers are supported capability.
     */

      char c = s.charAt(index);
      if (c >= safeOctets.length || !safeOctets[c]) {
        return escapeSlow(s, index);
      }
    }
    return s;
  }

  /** Escapes the given Unicode code point in UTF-8. */
  @Override
  protected char @Nullable [] escape(int cp) {
    // We should never get negative values here but if we do it will throw an

          || c > safeMaxChar
          || c < safeMinChar) {
        return escapeSlow(s, i);
      }
    }
    return s;
  }

  /**
   * Escapes a single Unicode code point using the replacement array and safe range values. If the
   * given character does not have an explicit replacement and lies outside the safe range then
   * {@link #escapeUnsafe} is called.
   *

            final int flags = getFlags();
            final boolean unicode = (flags & NTLMSSP_NEGOTIATE_UNICODE) != 0;
            final String oem = unicode ? null : getOEMEncoding();
            final String domainName = getDomain();
            byte[] domain = null;
            if (domainName != null && domainName.length() != 0) {
                domain = unicode ? domainName.getBytes(UNI_ENCODING) : domainName.getBytes(oem);
            }

        E(p21, challenge, p24);
        return p24;
    }

    /**
     * Generate the Unicode MD4 hash for the password associated with these credentials.
     *
     * @param password the password to hash
     * @param challenge the server challenge bytes
     * @return the Unicode MD4 hash response
     */
    static public byte[] getNTLMResponse(final String password, final byte[] challenge) {