Jetpack_WPES_Search_Query_Parser::remaining_prefix_query()

Complexity

Conditions	11
Paths	41

Size

Total Lines	141
Code Lines	75

Duplication

Lines	17
Ratio	12.06 %

Importance

Changes

0

<?php
	function remaining_prefix_query( $args ) {
		$defaults = array(
			'must_query_fields' => array( 'all_content' ),
			'boost_query_fields' => array( 'title' ),
			'boost_operator' => 'and',
			'boost_query_type' => 'best_fields',
		);
		$args = wp_parse_args( $args, $defaults );

		if ( empty( $this->current_query ) || ctype_space( $this->current_query ) ) {
			return;
		}

		//////////////////////////////////
		// Example cases to think about:
		// "elasticse"
		// "elasticsearch"
		// "elasticsearch "
		// "elasticsearch lucen"
		// "elasticsearch lucene"
		// "the future"  - note the stopword which will match nothing!
		// "F1" - an exact match that also has tons of expansions
		// "こんにちは" ja "hello"
		// "こんにちは友人" ja "hello friend" - we just rely on the prefix phrase and ES to split words
		//   - this could still be better I bet. Maybe we need to analyze with ES first?
		//

		/////////////////////////////
		//extract pieces of query
		// eg: "PREFIXREMAINDER PREFIXWORD"
		//     "elasticsearch lucen"

		$prefix_word = false;
		$prefix_remainder = false;

$prefix_remainder is not used, you could remove the assignment.

		if ( preg_match_all( '/([^ ]+)$/', $this->current_query, $matches ) ) {
			$prefix_word = $matches[1][0];
		}

		$prefix_remainder = preg_replace( '/([^ ]+)$/', '', $this->current_query );
		if ( ctype_space( $prefix_remainder ) ) {
			$prefix_remainder = false;
		}

		if ( ! $prefix_word ) {

The expression $prefix_word of type string|false is loosely compared to false; this is ambiguous if the string can be empty. You might want to explicitly use === false instead.

			//Space at the end of the query, so skip using a prefix query
			if ( ! empty( $args['must_query_fields'] ) ) {
				$this->add_query( array(
					'multi_match' => array(
						'fields' => $args['must_query_fields'],
						'query' => $this->current_query,
						'operator' => 'and',
					) ) );
			}

			if ( ! empty( $args['boost_query_fields'] ) ) {
				$this->add_query( array(
					'multi_match' => array(
						'fields' => $args['boost_query_fields'],
						'query' => $this->current_query,
						'operator' => $args['boost_operator'],
						'type' => $args['boost_query_type'],
					) ), 'should' );
			}
		} else {

			//must match the prefix word and the prefix remainder
			if ( ! empty( $args['must_query_fields'] ) ) {
				//need to do an OR across a few fields to handle all cases
				$must_q = array( 'bool' => array( 'should' => array( ), 'minimum_should_match' => 1 ) );

				//treat all words as an exact search (boosts complete word like "news"
				//from prefixes of "newspaper")
				$must_q['bool']['should'][] = array( 'multi_match' => array(
					'fields' => $this->all_fields,

The property all_fields does not exist. Did you maybe forget to declare it?

					'query' => $full_text,

The variable $full_text does not exist. Did you forget to declare it?

					'operator' => 'and',
					'type' => 'cross_fields',
				) );

				//always optimistically try and match the full text as a phrase
				//prefix "the futu" should try to match "the future"
				//otherwise the first stopword kinda breaks
				//This also works as the prefix match for a single word "elasticsea"
				$must_q['bool']['should'][] = array( 'multi_match' => array(
					'fields' => $this->phrase_fields,

The property phrase_fields does not exist. Did you maybe forget to declare it?

					'query' => $full_text,
					'operator' => 'and',
					'type' => 'phrase_prefix',
					'max_expansions' => 100,
				) );

				if ( $prefix_remainder ) {

The expression $prefix_remainder of type false|string is loosely compared to true; this is ambiguous if the string can be empty. You might want to explicitly use !== false instead.

					//Multiple words found, so treat each word on its own and not just as
					//a part of a phrase
					//"elasticsearch lucen" => "elasticsearch" exact AND "lucen" prefix
					$q['bool']['should'][] = array( 'bool' => array(

$q was never initialized. Although not strictly required by PHP, it is generally a good practice to add $q = array(); before regardless.

						'must' => array(
							array( 'multi_match' => array(
								'fields' => $this->phrase_fields,
								'query' => $prefix_word,
								'operator' => 'and',
								'type' => 'phrase_prefix',
								'max_expansions' => 100,
							) ),
							array( 'multi_match' => array(
								'fields' => $this->all_fields,
								'query' => $prefix_remainder,
								'operator' => 'and',
								'type' => 'cross_fields',
							) ),
						)
					) );
				}

				$this->add_query( $must_q );
			}

			//Now add any boosting of the query
			if ( ! empty( $args['boost_query_fields'] ) ) {
				//treat all words as an exact search (boosts complete word like "news"
				//from prefixes of "newspaper")
				$this->add_query( array(
					'multi_match' => array(
						'fields' => $args['boost_query_fields'],
						'query' => $this->current_query,
						'operator' => $args['boost_query_operator'],
						'type' => $args['boost_query_type'],
					) ), 'should' );

				//optimistically boost the full phrase prefix match
				$this->add_query( array(
					'multi_match' => array(
						'fields' => $args['boost_query_fields'],
						'query' => $this->current_query,
						'operator' => 'and',
						'type' => 'phrase_prefix',
						'max_expansions' => 100,
					) ) );
			}
		}
	}