问题
Below is my configurations and code. Basically I'm trying to fetch record from ES Indexes with typeahead search. Though single word search is working as expected, but only on a single field, the multi word search is not working at all.
My requirement is to fetch record basis on my searched word after searching for it on multiple fields. For example, if I search a name "Jason K Smith", the query should run on all the fields(name, address, second name, last name and so on...) as the searched text could be in multiple fields. Also, if I search for two names like "Mike John" the result should contain records for both the names(this I feel is possible, I may be wrong).
Below is my code:
hibernate.cfg.xml
<property name="hibernate.search.default.indexmanager">elasticsearch</property>
<property name="hibernate.search.default.elasticsearch.host">http://127.0.0.1:9200</property>
<property name="hibernate.search.default.elasticsearch.index_schema_management_strategy">drop-and-create</property>
<property name="hibernate.search.default.elasticsearch.required_index_status">yellow</property>
Entity Class
@Entity
@Indexed
public class MYClass {
private DBAccessStatus dBAccessStatus;
private String optname = "";
private String phone1 = "";
@Fields({
@Field(name = "clientname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "standardAnalyzer")),
@Field(name = "edgeNGramClientname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteEdgeAnalyzer")),
@Field(name = "nGramClientname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteNGramAnalyzer"))
})
private String clientname = "";
@Fields({
@Field(name = "firstname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "standardAnalyzer")),
@Field(name = "edgeNGramFirstName", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteEdgeAnalyzer")),
@Field(name = "nGramFirstName", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteNGramAnalyzer"))
})
private String firstname = "";
@Fields({
@Field(name = "midname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "standardAnalyzer")),
@Field(name = "edgeNGramMidname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteEdgeAnalyzer")),
@Field(name = "nGramMidname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteNGramAnalyzer"))
})
private String midname = "";
private String prefixnm = "";
private String suffixnm = "";
@Fields({
@Field(name = "longname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "standardAnalyzer")),
@Field(name = "edgeNGramLongname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteEdgeAnalyzer")),
@Field(name = "nGramLongname", index = Index.YES, store = Store.YES,
analyze = Analyze.YES, analyzer = @Analyzer(definition = "autocompleteNGramAnalyzer"))
})
private String longname = "";
Analyzer Definitions
@AnalyzerDefs({
@AnalyzerDef(name = "autocompleteEdgeAnalyzer",
// Split input into tokens according to tokenizer
tokenizer = @TokenizerDef(factory = KeywordTokenizerFactory.class),
filters = {
// Normalize token text to lowercase, as the user is unlikely to
// care about casing when searching for matches
@TokenFilterDef(factory = PatternReplaceFilterFactory.class, params = {
@Parameter(name = "pattern", value = "([^a-zA-Z0-9\\.])"),
@Parameter(name = "replacement", value = " "),
@Parameter(name = "replace", value = "all") }),
@TokenFilterDef(factory = LowerCaseFilterFactory.class),
@TokenFilterDef(factory = StopFilterFactory.class),
// Index partial words starting at the front, so we can provide
// Autocomplete functionality
@TokenFilterDef(factory = EdgeNGramFilterFactory.class, params = {
@Parameter(name = "minGramSize", value = "3"),
@Parameter(name = "maxGramSize", value = "50") }) }),
@AnalyzerDef(name = "autocompleteNGramAnalyzer",
// Split input into tokens according to tokenizer
tokenizer = @TokenizerDef(factory = StandardTokenizerFactory.class),
filters = {
// Normalize token text to lowercase, as the user is unlikely to
// care about casing when searching for matches
@TokenFilterDef(factory = WordDelimiterFilterFactory.class),
@TokenFilterDef(factory = LowerCaseFilterFactory.class),
@TokenFilterDef(factory = NGramFilterFactory.class, params = {
@Parameter(name = "minGramSize", value = "3"),
@Parameter(name = "maxGramSize", value = "5") }),
@TokenFilterDef(factory = PatternReplaceFilterFactory.class, params = {
@Parameter(name = "pattern", value = "([^a-zA-Z0-9\\.])"),
@Parameter(name = "replacement", value = " "),
@Parameter(name = "replace", value = "all") }) }),
@AnalyzerDef(name = "standardAnalyzer",
// Split input into tokens according to tokenizer
tokenizer = @TokenizerDef(factory = StandardTokenizerFactory.class),
filters = {
// Normalize token text to lowercase, as the user is unlikely to
// care about casing when searching for matches
@TokenFilterDef(factory = WordDelimiterFilterFactory.class),
@TokenFilterDef(factory = LowerCaseFilterFactory.class),
@TokenFilterDef(factory = PatternReplaceFilterFactory.class, params = {
@Parameter(name = "pattern", value = "([^a-zA-Z0-9\\.])"),
@Parameter(name = "replacement", value = " "),
@Parameter(name = "replace", value = "all") }) }),
@AnalyzerDef(name = "textanalyzer", tokenizer = @TokenizerDef(factory = StandardTokenizerFactory.class), filters = {
@TokenFilterDef(factory = LowerCaseFilterFactory.class),
@TokenFilterDef(factory = SnowballPorterFilterFactory.class, params = {
@Parameter(name = "language", value = "English") }) }) // Def
})
Search Results example
{
"_index" : "com.csc.pt.svc.data.to.bascltj001to",
"_type" : "com.csc.pt.svc.data.to.Bascltj001TO",
"_id" : "44,13",
"_score" : 1.0,
"_source" : {
"id" : "44,13",
"cltseqnum" : 44,
"addrseqnum" : "13",
"clientname" : "Thompsan 1",
"edgeNGramClientname" : "Thompsan 1",
"nGramClientname" : "Thompsan 1",
"firstname" : "Robert",
"edgeNGramFirstName" : "Robert",
"nGramFirstName" : "Robert",
"longname" : "Robert Thompsan",
"edgeNGramLongname" : "Robert Thompsan",
"nGramLongname" : "Robert Thompsan",
"addrln1" : "1 Main Street",
"edgeNGramAddrln1" : "1 Main Street",
"nGramAddrln1" : "1 Main Street",
"city" : "Columbia",
"edgeNGramCity" : "Columbia",
"nGramCity" : "Columbia",
"state" : "SC",
"edgeNGramState" : "SC",
"nGramState" : "SC",
"zipcode" : "29224",
"edgeNGramZipcode" : "29224",
"nGramZipcode" : "29224",
"country" : "USA",
"edgeNGramCountry" : "USA",
"nGramCountry" : "USA"
}
},
Current applied code:
protected static final String FIRSTNAME_EDGE_NGRAM_INDEX = "edgeNGramFirstName";
protected static final String FIRSTNAME_NGRAM_INDEX = "nGramFirstName";
protected static final String MIDNAME_EDGE_NGRAM_INDEX = "edgeNGramMidname";
protected static final String MIDNAME_NGRAM_INDEX = "nGramMidname";
protected static final String PHONE1_EDGE_NGRAM_INDEX = "edgeNGramPhone1";
protected static final String PHONE1_NGRAM_INDEX = "nGramPhone1";
protected static final String LONGNAME_EDGE_NGRAM_INDEX = "edgeNGramLongname";
protected static final String LONGNAME_NGRAM_INDEX = "nGramLongname";
protected static final String CLIENT_EDGE_NGRAM_INDEX = "edgeNGramClientname";
protected static final String CLIENT_NGRAM_INDEX = "nGramClientname";
protected static final String ADDRLN1_EDGE_NGRAM_INDEX = "edgeNGramAddrln1";
protected static final String ADDRLN1_NGRAM_INDEX = "nGramAddrln1";
protected static final String ADDRLN2_EDGE_NGRAM_INDEX = "edgeNGramAddrln2";
protected static final String ADDRLN2_NGRAM_INDEX = "nGramAddrln2";
protected static final String ADDRLN3_EDGE_NGRAM_INDEX = "edgeNGramAddrln3";
protected static final String ADDRLN3_NGRAM_INDEX = "nGramAddrln3";
protected static final String ADDRLN4_EDGE_NGRAM_INDEX = "edgeNGramAddrln4";
protected static final String ADDRLN4_NGRAM_INDEX = "nGramAddrln4";
protected static final String CITY_EDGE_NGRAM_INDEX = "edgeNGramCity";
protected static final String CITY_NGRAM_INDEX = "nGramCity";
protected static final String STATE_EDGE_NGRAM_INDEX = "edgeNGramState";
protected static final String STATE_NGRAM_INDEX = "nGramState";
protected static final String COUNTRY_EDGE_NGRAM_INDEX = "edgeNGramCountry";
protected static final String COUNTRY_NGRAM_INDEX = "nGramCountry";
protected void getClt0100Data(){
Query query = queryBuilder.phrase().withSlop(5).
onField(FIRSTNAME_EDGE_NGRAM_INDEX).andField(FIRSTNAME_NGRAM_INDEX)
.andField(MIDNAME_EDGE_NGRAM_INDEX).andField(MIDNAME_NGRAM_INDEX)
.andField(LONGNAME_EDGE_NGRAM_INDEX).andField(LONGNAME_NGRAM_INDEX)
.andField(CLIENT_EDGE_NGRAM_INDEX).andField(CLIENT_NGRAM_INDEX)
.andField(ADDRLN1_EDGE_NGRAM_INDEX).andField(ADDRLN1_NGRAM_INDEX)
.andField(ADDRLN2_EDGE_NGRAM_INDEX).andField(ADDRLN2_NGRAM_INDEX)
.andField(ADDRLN3_EDGE_NGRAM_INDEX).andField(ADDRLN3_NGRAM_INDEX)
.andField(ADDRLN4_EDGE_NGRAM_INDEX).andField(ADDRLN4_NGRAM_INDEX)
.andField(CITY_EDGE_NGRAM_INDEX).andField(CITY_NGRAM_INDEX)
.andField(STATE_EDGE_NGRAM_INDEX).andField(STATE_NGRAM_INDEX)
.andField(COUNTRY_EDGE_NGRAM_INDEX).andField(COUNTRY_NGRAM_INDEX)
.boostedTo(5).sentence(this.data.getSearchText().toLowerCase()).createQuery();
FullTextQuery fullTextQuery = fullTextSession.createFullTextQuery(query, Bascltj001TO.class);
fullTextQuery.setMaxResults(this.data.getPageSize()).setFirstResult(this.data.getPageSize())
.setProjection("longname, firstname", "cltseqnum", "midname", "clientname", "addrln1","addrln2","addrln3","addrln4","city","state","zipcode", "country")
.setResultTransformer( new BasicTransformerAdapter() {
@Override
public Cltj001ElasticSearchResponseTO transformTuple(Object[] tuple, String[] aliases) {
return new Cltj001ElasticSearchResponseTO((String) tuple[0], (String) tuple[1], (long) tuple[2], (String) tuple[3], (String) tuple[4],
(String) tuple[5],(String) tuple[6],(String) tuple[7],(String) tuple[8],(String) tuple[9], (String) tuple[10], (String) tuple[11], (String) tuple[12]);
}
});
resultsClt0100List = fullTextQuery.getResultList();
}
回答1:
What you're doing is weird.
I don't see why you use ngram if in the end you want to do a phrase search. I don't think that will work very well.
I think simple query strings are more what you're looking for: https://docs.jboss.org/hibernate/search/5.8/reference/en-US/html_single/#_simple_query_string_queries .
But then again, you're using ngram everywhere whereas what you describe as the feature you want doesn't really need ngrams as it seems you're expecting an exact search.
I would recommend you to start simple and use an analyzer removing the accents and lowercasing the text and make it work.
And then consider ngrams if you really want some sort of fuzzy search.
来源：https://stackoverflow.com/questions/51835264/typeahead-search-not-working-for-multiple-wordswith-space-through-lucene-hiber