* either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.client.fs;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URLEncoder;

     */
    private void copy(final SmbFile src, final File dest) {
        if (dest.exists() && !dest.canWrite()) {
            return;
        }
        try (BufferedInputStream in = new BufferedInputStream(new SmbFileInputStream(src));
                BufferedOutputStream out = new BufferedOutputStream(new FileOutputStream(dest))) {
            final byte[] buf = new byte[1024];
            int length;

        if (in == null) {
            throw new CrawlerSystemException("XML input stream is null. Cannot extract text from null input.");
        }
        try {
            final BufferedInputStream bis = new BufferedInputStream(in);
            final String enc = getEncoding(bis);
            final String content = UNESCAPE_HTML4.translate(new String(InputStreamUtil.getBytes(bis), enc));
            return createExtractData(content);

     * @throws CurlException if an error occurs while accessing the content.
     */
    public String getContentAsString() {
        final byte[] bytes = new byte[4096];
        try (BufferedInputStream bis = new BufferedInputStream(getContentAsStream());
                ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
            int length = bis.read(bytes);
            while (length != -1) {

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper.impl;

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.BufferedInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;

     */
    private void copy(final SmbFile src, final File dest) {
        if (dest.exists() && !dest.canWrite()) {
            return;
        }
        try (BufferedInputStream in = new BufferedInputStream(new SmbFileInputStream(src));
                BufferedOutputStream out = new BufferedOutputStream(new FileOutputStream(dest))) {
            final byte[] buf = new byte[1024];
            int length;

 */
package org.codelibs.core.io;

import static org.codelibs.core.misc.AssertionUtil.assertArgumentNotEmpty;
import static org.codelibs.core.misc.AssertionUtil.assertArgumentNotNull;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;
import java.net.URL;

     * @return true if the stream contains valid sitemap data, false otherwise
     */
    protected boolean isValid(final InputStream in, final boolean recursive) {
        final BufferedInputStream bis = new BufferedInputStream(in);
        bis.mark(preloadSize);

        final byte[] bytes = new byte[preloadSize];
        try {
            if (bis.read(bytes) == -1) {
                return false;
            }

         *
         * @param handler the input stream supplier
         */
        private void writeContent(final Supplier<InputStream> handler) {
            try (BufferedInputStream bis = new BufferedInputStream(handler.get());
                    ContentOutputStream dfos = new ContentOutputStream(threshold, Curl.tmpDir)) {
                final byte[] bytes = new byte[4096];