etext - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MsExcelExtractor.java

import org.codelibs.fess.crawler.exception.ExtractException;

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

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {
        super();
    }

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/ajax/index.html

<!DOCTYPE html>
<html>
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
    <title>Ajax Test</title>
    <script language="javascript" src="js/jquery-2.1.1.min.js" type="text/javascript"></script>
    <script language="javascript" src="js/test.js" type="text/javascript"></script>
</head>
<body>
    <div id="header">
        <h1>Ajax Test Site</h1>
    </div>
    <div id="menubar">
        <ul>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 1.5K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/normalizer/ICUNormalizer.java

 */
package org.codelibs.fess.suggest.normalizer;

import com.ibm.icu.text.Transliterator;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *
 * <p>This class uses a specified Transliterator to perform text normalization.
 * The Transliterator is initialized with a given ID during the construction of

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Fri Jul 04 14:00:23 UTC 2025

- 1.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TextUtil.java

import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 12K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/TextTransformer.java

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 6.5K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/test/java/org/codelibs/fess/suggest/SuggesterBuilderTest.java

            public void init() throws IOException {

            }

            @Override
            public List<String> convert(String text, final String field, String... langs) throws IOException {
                return null;
            }
        };

        final Normalizer normalizer = (text, field, lang) -> null;

        final Suggester suggester = Suggester.builder()

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Thu Aug 07 02:41:28 UTC 2025

- 3.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractorTest.java

                    ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

                })//
        ;

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 3.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TextExtractor.java

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

/**
 * Extracts text content from an input stream as plain text.
 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**
     * Creates a new TextExtractor instance.
     */

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 2K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/settings/AnalyzerSettings.java

        /**
         * Analyzes the given text.
         * @param text The text to analyze.
         * @param field The field name.
         * @param lang The language.
         * @return A list of analyzed tokens.
         */
        @Override
        public List<AnalyzeToken> analyze(final String text, final String field, final String lang) {
            if (text == null || text.length() > maxContentLenth) {

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Thu Aug 07 02:41:28 UTC 2025

- 26.5K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

src/main/java/org/codelibs/fess/suggest/converter/ReadingConverter.java

    void init() throws IOException;

    /**
     * Converts the given text into a list of readings based on the specified field and languages.
     *
     * @param text the text to be converted.
     * @param field the field to be used for conversion.
     * @param langs the languages to be used for conversion.
     * @return a list of readings for the given text.
     * @throws IOException if an I/O error occurs during conversion.
     */

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Sat Mar 15 06:51:20 UTC 2025

- 1.6K bytes

- Viewed (0)

Search Options