* character encoding. UTF-8 is defined in section D92 of <a
 * href="http://www.unicode.org/versions/Unicode6.2.0/ch03.pdf">The Unicode Standard Core
 * Specification, Chapter 3</a>.
 *
 * <p>The variant of UTF-8 implemented by this class is the restricted definition of UTF-8
 * introduced in Unicode 3.1. One implication of this is that it rejects <a
 * href="http://www.unicode.org/versions/corrigendum1.html">"non-shortest form"</a> byte sequences,

    // The char values \uFFFE and \uFFFF are explicitly not allowed in XML
    // (Unicode code points above \uFFFF are represented via surrogate pairs
    // which means they are treated as pairs of safe characters).
    builder.setSafeRange(Character.MIN_VALUE, '\uFFFD');
    // Unsafe characters are replaced with the Unicode replacement character.
    builder.setUnsafeReplacement("\uFFFD");

    /*

            if( useUnicode ) {
                // should Unicode alignment be corrected for here?
                str = new String( src, srcIndex, len, UNI_ENCODING );
            } else {
    
                /* On NT without Unicode the fileNameLength
                 * includes the '\0' whereas on win98 it doesn't. I
                 * guess most clients only support non-unicode so
                 * they don't run into this.

	"io"
	"strings"
	"testing"
	"unicode"
	"unicode/utf8"
)

const smallMaxTokenSize = 256 // Much smaller for more efficient testing.

// Test white space table matches the Unicode definition.
func TestSpace(t *testing.T) {
	for r := rune(0); r <= utf8.MaxRune; r++ {
		if IsSpace(r) != unicode.IsSpace(r) {
			t.Fatalf("white space property disagrees: %#U should be %t", r, unicode.IsSpace(r))
		}
	}
}

import junit.framework.TestCase;

/**
 * Unit test for {@link Ascii}.
 *
 * @author Craig Berry
 */
@GwtCompatible
public class AsciiTest extends TestCase {

  /**
   * The Unicode points {@code 00c1} and {@code 00e1} are the upper- and lowercase forms of
   * A-with-acute-accent, {@code Á} and {@code á}.
   */
  private static final String IGNORED = "`10-=~!@#$%^&*()_+[]\\{}|;':\",./<>?'\u00c1\u00e1\n";

            }
        }
        else {
            this.useUnicode = ctx.getConfig().isUseUnicode();
        }

        if ( this.useUnicode ) {
            log.debug("Unicode is enabled");
        }
        else {
            log.debug("Unicode is disabled");
        }
        return true;
    }


    /**
     * {@inheritDoc}
     *

 *
 * <p><b>Warning:</b> This class deals only with {@code char} values, that is, <a
 * href="http://www.unicode.org/glossary/#BMP_character">BMP characters</a>. It does not understand
 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">supplementary Unicode code
 * points</a> in the range {@code 0x10000} to {@code 0x10FFFF} which includes the majority of

pkg unicode, const Version = "15.0.0" #55079
pkg unicode, var Cypro_Minoan *RangeTable #55079
pkg unicode, var Kawi *RangeTable #55079
pkg unicode, var Nag_Mundari *RangeTable #55079
pkg unicode, var Old_Uyghur *RangeTable #55079
pkg unicode, var Tangsa *RangeTable #55079
pkg unicode, var Toto *RangeTable #55079

pkg text/template/parse, type Node interface { Copy, String, Type }
pkg unicode, const Version = "10.0.0"
pkg unicode, const Version = "11.0.0"
pkg unicode, const Version = "12.0.0"
pkg unicode, const Version = "13.0.0"
pkg unicode, const Version = "6.2.0"
pkg unicode, const Version = "6.3.0"
pkg unicode, const Version = "7.0.0"
pkg unicode, const Version = "8.0.0"
pkg unicode, const Version = "9.0.0"

<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>