com.xlrit.gears.engine.search.PostgresSearchAdapter Maven / Gradle / Ivy

Go to download
package com.xlrit.gears.engine.search;

import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;

import com.xlrit.gears.base.repository.JpaRepository;
import com.xlrit.gears.engine.meta.EntityInfo;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * A tsquery value stores lexemes that are to be searched for, and can combine them using the Boolean operators & (AND), | (OR), and ! (NOT), as well as the phrase search operator <-> (FOLLOWED BY).
 * There is also a variant  of the FOLLOWED BY operator, where N is an integer constant that specifies the distance between the two lexemes being searched for. <-> is equivalent to <1>.
 * 
 * to_tsquery creates a tsquery value from querytext, which must consist of single tokens separated by the tsquery operators & (AND), | (OR), ! (NOT), and <-> (FOLLOWED BY), possibly grouped using parentheses.
 * In other words, the input to to_tsquery must already follow the general rules for tsquery input, as described in Section 8.11.2.
 * The difference is that while basic tsquery input takes the tokens at face value, to_tsquery normalizes each token into a lexeme using the specified or default configuration, and discards any tokens that are stop words according to the configuration.
 */
public class PostgresSearchAdapter extends DefaultSearchAdapter {
	private static final Logger LOG = LoggerFactory.getLogger(PostgresSearchAdapter.class);

	private final String searchLanguage;

	public PostgresSearchAdapter(String defaultMode, String searchLanguage) {
		super(defaultMode);
		this.searchLanguage = searchLanguage;
	}

	@Override
	public void logSearchIndex(String name, EntityInfo entityInfo, List fieldNames) {
		if (entityInfo.getRepository() instanceof JpaRepository repository) {
			String tableName = repository.getTableName();
			String indexName = tableName + "_search";
			List columnNames = repository.getColumnNames(fieldNames);

			if (tableName != null && columnNames != null) {
				LOG.info("CREATE INDEX {} ON {} USING GIN (to_tsvector('{}', concat_ws(' ', {})));", indexName, tableName, searchLanguage, String.join(", ", columnNames));
			}
			else {
				LOG.info("-- Unable to generate search index for {} (tableName={}, columnNames={})", name, tableName, columnNames);
			}
		}
	}

	@Override
	protected String toAdvancedSearchTerm(String querytext) {
		// adapt the search input as an argument to `to_tsquery`
		// special characters: - _ . ( ) & # + TODO what about "/" and ","?
		// we can keep . but need to escape the rest
		String stripped = querytext.replaceAll("([-_()&#!])", "\\\\$1");
		String[] words = stripped.split("\\s+");

		return Arrays.stream(words)
			.map(word -> word + ":*")
			.collect(Collectors.joining(" & "));
	}

	@Override
	public String toString() {
		return "PostgresSearchAdapter[" +
			"language='" + searchLanguage + '\'' +
			']';
	}
}