.sum();

            analysis.add(new PathAnalysis(
                    path,
                    uniqueStrings,
                    totalOccurrences,
                    totalMemory,
                    potentialSavings,
                    (double) totalOccurrences / uniqueStrings,
                    getMostFrequentValues(stats, 5)));
        }

```

## Optional: Search Analysis Support

If your language requires special text analysis (stemming, stop words, etc.), you may need to configure OpenSearch analyzers.

### 1. Update OpenSearch Index Template

Edit `src/main/resources/fess_indices/fess.json` to add language-specific analyzers.

**Example for Swedish:**
```json
{
  "analysis": {
    "filter": {
      "swedish_stop": {

                .put("analysis.analyzer.test_reading_analyzer.type", "custom")
                .put("analysis.analyzer.test_reading_analyzer.tokenizer", "standard")
                .put("analysis.analyzer.test_reading_term_analyzer.type", "custom")
                .put("analysis.analyzer.test_reading_term_analyzer.tokenizer", "standard")
                .put("analysis.analyzer.test_reading_analyzer_ja.type", "custom")

import java.util.Comparator;
import java.util.List;
import java.util.PriorityQueue;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.store.ByteArrayDataInput;

     * @param analyzer Analyzer
     * @param field Field
     * @param lang Language
     * @param useReading Whether to use reading analysis
     * @param tokens Token list to add to
     * @param buf Buffer containing text
     * @param analyzeType Type of analysis (for logging)
     * @param isLast Whether this is the last buffer
     */

        data.putValue("author", "Jane Smith");
        data.putValue("date", "2025-01-15");

        // Add multiple values
        String[] keywords = { "business", "report", "analysis", "2025" };
        data.putValues("keywords", keywords);

        String[] passwords = { "secret123", "pass456" };
        data.putValues(ExtractData.FILE_PASSWORDS, passwords);

        // Verify content

 *   <li>Concurrent crawler process management with configurable limits</li>
 *   <li>Selective crawling based on configuration IDs</li>
 *   <li>Document expiration handling</li>
 *   <li>Hot thread monitoring for performance analysis</li>
 *   <li>Process isolation with separate JVM</li>
 * </ul>
 */
public class CrawlJob extends ExecJob {

    private static final Logger logger = LogManager.getLogger(CrawlJob.class);

    /**

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.query.parser;

import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser.Operator;

## Technology Stack

- **Java**: 21+ (configured via parent POM)
- **OpenSearch**: Latest (provided scope)
- **Apache Lucene**: Query parsing and text analysis
- **ICU4J**: Unicode text processing and normalization
- **JUnit 4**: Testing framework
- **Maven**: Build and dependency management

## Quick Start

### Prerequisites

- Java 21 or higher

import java.util.regex.Pattern;
import java.util.stream.Stream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.suggest.analysis.SuggestAnalyzer;
import org.codelibs.fess.suggest.constants.FieldNames;
import org.codelibs.fess.suggest.exception.SuggestSettingsException;
import org.codelibs.fess.suggest.util.SuggestUtil;