import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */
public class MsPublisherExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPublisherExtractor instance.
     */

                if (c == spaceChar) {
                    return true;
                }
            }
            return false;
        }

        /**
         * Sets the initial capacity for the text normalization context.
         *
         * @param initialCapacity the initial capacity to be set
         * @return the updated TextNormalizeContext instance
         */

        return ruleId;
    }

    /**
     * Sets the rule ID for this rule.
     *
     * @param ruleId the rule ID to set
     */
    public void setRuleId(final String ruleId) {
        this.ruleId = ruleId;
    }

    @Override
    public ResponseProcessor getResponseProcessor() {
        return responseProcessor;
    }

    /**
     * Sets the response processor for this rule.
     *

    }

    /**
     * Sets the MIME type of the content to extract.
     *
     * @param mimeType the MIME type to set
     * @return this builder instance for method chaining
     */
    public ExtractorBuilder mimeType(final String mimeType) {
        this.mimeType = mimeType;
        return this;
    }

    /**
     * Sets the filename of the content to extract.
     *

    public boolean isIncludeAware() {
        return includeAware;
    }

    /**
     * Sets the includeAware.
     *
     * @param includeAware the includeAware to set
     */
    public void setIncludeAware(final boolean includeAware) {
        this.includeAware = includeAware;
    }

    /**
     * Sets the cache duration.
     * @param cacheDuration The cache duration in minutes.
     */

            this.userAgent = userAgent;
        }

        /**
         * Sets the crawl delay for this directive.
         * @param crawlDelay the crawl delay in seconds
         */
        public void setCrawlDelay(final int crawlDelay) {
            this.crawlDelay = crawlDelay;
        }

        /**
         * Gets the crawl delay for this directive.
         * @return the crawl delay in seconds
         */

     */
    public String getCharset() {
        return charset;
    }

    /**
     * Sets the character set used for SMB1 operations.
     *
     * @param charset the charset to set
     */
    public void setCharset(final String charset) {
        this.charset = charset;
    }

    /**
     * Sets the SMB1 authentication holder.
     *

        return IDN.toASCII(decode(host), flag);
    }

    /**
     * Sets the flag for IDN conversion.
     *
     * @param flag the flag to set
     */
    public void setFlag(final int flag) {
        this.flag = flag;
    }

    /**
     * Sets the encoding for URL decoding.
     *
     * @param encoding the encoding to set
     */

                throw new ExtractException("Could not extract a content.", e);
            }
        }

        return new ExtractData(buf.toString().trim());
    }

    /**
     * Sets the maximum content size.
     * @param maxContentSize The maximum content size to set.
     */
    public void setMaxContentSize(final long maxContentSize) {
        this.maxContentSize = maxContentSize;
    }

            }
        } finally {
            CloseableUtil.closeQuietly(ais);
        }

        return buf.toString().trim();
    }

    /**
     * Sets the maximum content size.
     * @param maxContentSize The maximum content size to set.
     */
    public void setMaxContentSize(final long maxContentSize) {
        this.maxContentSize = maxContentSize;
    }