* limitations under the License.
 */

package com.google.common.testing;

import static com.google.common.truth.Truth.assertThat;
import static java.nio.charset.StandardCharsets.UTF_8;
import static java.util.concurrent.TimeUnit.SECONDS;
import static org.junit.Assert.assertThrows;

import com.google.common.base.CharMatcher;
import com.google.common.base.Equivalence;

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");
        final BufferedInputStream bis = new BufferedInputStream(in);

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
  <!-- do_not_remove: published-with-gradle-metadata -->
  <modelVersion>4.0.0</modelVersion>
  <parent>
    <groupId>com.google.guava</groupId>
    <artifactId>guava-parent</artifactId>

   * reality there are optimizations that make the getBytes(Charset) approach considerably faster,
   * at least for commonly used charsets like UTF-8.
   */

  @Override
  @CanIgnoreReturnValue
  public final Hasher putByte(byte b) {
    buffer.put(b);
    munchIfFull();
    return this;
  }

  @Override
  @CanIgnoreReturnValue

            builder.endObject();
            builder.flush();
            try (OutputStream out = builder.getOutputStream()) {
                stats = ((ByteArrayOutputStream) out).toString(Constants.UTF_8);
            }
        } catch (final Exception e) {
            appendException(buf, e).append(',');
        }
        buf.append("\"search_engine\":").append(stats).append(',');
    }

            public void write(final int b) throws IOException {
                if (b == '\n' || b == '\r' || buf.size() >= MAX_LEN) {
                    try {
                        final String msg = buf.toString(Constants.UTF_8);
                        if (StringUtil.isNotBlank(msg)) {
                            if (logger.isTraceEnabled()) {
                                logger.trace(msg);

   *
   * <p><b>Warning:</b> This method will produce different output than most other languages do when
   * running on the equivalent input. For cross-language compatibility, use {@link #putString},
   * usually with a charset of UTF-8. For other use cases, use {@code putUnencodedChars}.
   *
   * @since 15.0 (since 11.0 as putString(CharSequence))
   */
  @CanIgnoreReturnValue
  PrimitiveSink putUnencodedChars(CharSequence charSequence);

 *
 */
public abstract class SystemUtil {

    /**
     * Do not instantiate.
     */
    protected SystemUtil() {
    }

    /**
     * <code>file.encoding</code> system property. Example: UTF-8
     */
    public static final String FILE_ENCODING = System.getProperty("file.encoding");

    /**
     * <code>line.separator</code> system property. For example, on Mac OS X: <code>"\n"</code>
     */

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<artifactId>fess-suggest</artifactId>
	<version>15.3.0-SNAPSHOT</version>
	<packaging>jar</packaging>
	<name>fess-suggest</name>
	<url>https://fess.codelibs.org/</url>

    }

    public void test_getTika_xml_broken() throws UnsupportedEncodingException {
        final InputStream in = new ByteArrayInputStream("<?xml encoding=\"UTF-8\"/><hoge>テスト<br></hoge>".getBytes(Constants.UTF_8));
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);