I have such a problem. There is a product: Папір офісний Double A, A5 (148 х 210 мм), Premium 80г/м2 500 аркушів
I make a search request: Папір офісний 500 аркушів
- everything is fine, it is found.
But when I make a request: Папір офісний на 500 аркушів
- the product is not found.
What could be the problem. I try to add it to stopwords
but it doesn't give any result.
I need such words as: "on", "in", "and"... Did not affect the search query in any way. They were generally ignored in the search query
Image: elasticsearch:7.9.1
Here is the code to build the index:
public function createIndex()
{
$mappingParams = [
'index' => $this->getIndexName(),
'body' => [
'mappings' => [
'_source' => [
'enabled' => true
],
'properties' => $this->getMappingProperties(),
],
'settings' => [
'analysis' => [
'normalizer' => [
'lowercase_keyword' => [
'type' => 'custom',
'filter' => ['lowercase', 'trim'],
],
],
'tokenizer' => [
'ngram_tokenizer' => [
'type' => 'edge_ngram',
'min_gram' => 1,
'max_gram' => 15,
'token_chars' => [
'letter',
'digit',
],
],
],
'filter' => [
'synonym_filter' => [
'type' => 'synonym',
'synonyms' => [
'аркуш, сторінка', 'арк, ст', 'аркуш, ст', 'сторінка, арк', 'автомобіль, машина',
'тетрадь, зошит', 'кошелек, гаманець', 'на' => ' ',
],
],
'uk_stopwords' => [
'type' => 'stop',
'stopwords' => ['на', 'та', 'і', 'at', 'TY358'],
],
],
'analyzer' => [
'ngram_analyzer' => [
'type' => 'custom',
'tokenizer' => 'ngram_tokenizer',
'filter' => [
'lowercase',
'trim',
'synonym_filter',
'uk_stopwords',
'stop',
],
],
],
],
'index' => [
'max_result_window' => intval(\Variable::getArray('settings.elasticsearch.index_size', 100000)),
],
],
],
];
return $this->getClient()?->indices()->create($mappingParams);
}
Here is the mapping for the index:
protected array $mappingProperties = [
'id' => [
'type' => 'keyword',
],
'name' => [
'type' => 'text',
'fielddata' => true,
'analyzer' => 'ngram_analyzer',
'search_analyzer' => 'standard',
'fields' => [
'keyword' => [
'type' => 'keyword',
'normalizer' => 'lowercase_keyword',
]
],
],
'name_ru' => [
'type' => 'text',
'fielddata' => true,
'analyzer' => 'ngram_analyzer',
'search_analyzer' => 'standard',
'fields' => [
'keyword' => [
'type' => 'keyword',
'normalizer' => 'lowercase_keyword',
]
],
],
'body' => [
'type' => 'text',
],
'body_ru' => [
'type' => 'text',
],
'price' => [
'type' => 'object',
],
'extern_id' => [
'type' => 'keyword',
'fields' => [
'long' => [
'type' => 'long',
]
],
],
'gtin' => [
'type' => 'keyword',
],
'artikul' => [
'type' => 'text',
'fielddata' => true,
'fields' => [
'keyword' => [
'type' => 'keyword',
'normalizer' => 'lowercase_keyword',
]
],
],
'gpc' => [
'type' => 'integer',
],
'rating' => [
'type' => 'float',
],
'status' => [
'type' => 'keyword',
],
'availability' => [
'type' => 'integer',
],
'created_at' => [
'type' => 'date',
],
'category_id' => [
'type' => 'keyword',
],
'categories_ids' => [
'type' => 'keyword',
],
'brand_id' => [
'type' => 'keyword',
],
'properties' => [
'type' => 'object',
],
'is_feed' => [
'type' => 'boolean',
],
'is_prior' => [
'type' => 'boolean',
],
'is_new' => [
'type' => 'boolean',
],
'is_action' => [
'type' => 'boolean',
],
'is_popular' => [
'type' => 'boolean',
],
'is_showonmain' => [
'type' => 'boolean',
],
'is_freedelivery' => [
'type' => 'boolean',
],
'has_in_gurt' => [
'type' => 'boolean',
],
'has_in_fop' => [
'type' => 'boolean',
],
];
This is how a search query is built by name (text field):
$scoreSort = false;
$query = [];
if ($value = Arr::get($params, 'q')) {
$termQuery = [
'query' => [
'term' => [
'extern_id' => [
'value' => $value
]
]
]
];
$termResponse = $this->searchOnElasticsearch($termQuery);
$scoreSort = true;
if ($termResponse['hits']['total']['value'] > 0) {
$query['query']['bool']['must'][] = [
'term' => [
'extern_id' => substr($value, 0, 100)
]
];
} else {
if (($locale = app()->getLocale()) === 'uk') {
$nameField = 'name';
$fields = ['extern_id^15', 'gtin^10', 'artikul^10', "{$nameField}^5"];
} else {
$nameField = "name_{$locale}";
$fields = ['extern_id^15', 'gtin^10', 'artikul^10', "{$nameField}^5"];
}
$query['query']['bool']['must'][] = [
'bool' => [
'should' => [
[
'term' => [
"{$nameField}.keyword" => $value
]
],
[
'multi_match' => [
'fields' => $fields,
'query' => substr($value, 0, 100),
'fuzziness' => $this->getFuzziness(substr($value, 0, 100)),
'prefix_length' => 3,
'operator' => 'AND',
'analyzer' => 'ngram_analyzer',
],
]
]
]
];
}
}