lucene的suggest(搜索提示功能的实现）

<!-- https://mvnrepository.com/artifact/org.apache.lucene/lucene-suggest --><!-- 搜索提示 --><dependency>　　<groupId>org.apache.lucene</groupId>　　<artifactId>lucene-suggest</artifactId>　　<version>7.2.1</version></dependency>

public interface InputIterator extends BytesRefIterator { ???InputIterator EMPTY = new InputIterator.InputIteratorWrapper(BytesRefIterator.EMPTY); ???long weight(); ???BytesRef payload(); ???boolean hasPayloads(); ???Set<BytesRef> contexts(); ???boolean hasContexts(); ???public static class InputIteratorWrapper implements InputIterator { ???????private final BytesRefIterator wrapped; ???????public InputIteratorWrapper(BytesRefIterator wrapped) { ???????????this.wrapped = wrapped; ???????} ???????public long weight() { ???????????return 1L; ???????} ???????public BytesRef next() throws IOException { ???????????return this.wrapped.next(); ???????} ???????public BytesRef payload() { ???????????return null; ???????} ???????public boolean hasPayloads() { ???????????return false; ???????} ???????public Set<BytesRef> contexts() { ???????????return null; ???????} ???????public boolean hasContexts() { ???????????return false; ???????} ??}

BufferedInputIterator：对二进制类型的输入进行轮询； DocumentInputIterator：从索引中被store的field中轮询； FileIterator：从文件中每次读出单行的数据轮询，以\t进行间隔（且\t的个数最多为2个）； HighFrequencyIterator：从索引中被store的field轮询，忽略长度小于设定值的文本； InputIteratorWrapper：遍历BytesRefIterator并且返回的内容不包含payload且weight均为1； SortedInputIterator：二进制类型的输入轮询且按照指定的comparator算法进行排序；

RAMDirectory indexDir = new RAMDirectory(); ???????????StandardAnalyzer analyzer = new StandardAnalyzer(); ???????????AnalyzingInfixSuggester suggester = new AnalyzingInfixSuggester(indexDir, analyzer); ???????????// 创建索引,根据InputIterator的具体实现决定数据源以及创建索引的规则 ???????????suggester.build(new InputIterator{});

private static void lookup(AnalyzingInfixSuggester suggester, String name, ??????????????????????????????String region) throws IOException { ???????HashSet<BytesRef> contexts = new HashSet<BytesRef>(); ???????//使用Contexts域对suggest结果进行过滤 ???????contexts.add(new BytesRef(region.getBytes("UTF8"))); ???????//num决定了返回几条数据，参数四表明是否所有TermQuery是否都需要满足，参数五表明是否需要高亮显示 ???????List<Lookup.LookupResult> results = suggester.lookup(name, contexts, 2, true, false); ???????System.out.println("-- \"" + name + "\" (" + region + "):"); ???????for (Lookup.LookupResult result : results) { ???????????System.out.println(result.key);//result.key中存储的是根据用户输入内部算法进行匹配后返回的suggest内容 ???}

package com.cfh.study.lucence_test6;import java.io.Serializable;/** * @Author: cfh * @Date: 2018/9/17 10:18 * @Description: 用来测试suggest功能的pojo类 */public class Product implements Serializable { ???/** 产品名称 */ ???private String name; ???/** 产品图片 */ ???private String image; ???/** 产品销售地区 */ ???private String[] regions; ???/** 产品销售量 */ ???private int numberSold; ???public Product() { ???} ???public Product(String name, String image, String[] regions, int numberSold) { ???????this.name = name; ???????this.image = image; ???????this.regions = regions; ???????this.numberSold = numberSold; ???} ???public String getName() { ???????return name; ???} ???public void setName(String name) { ???????this.name = name; ???} ???public String getImage() { ???????return image; ???} ???public void setImage(String image) { ???????this.image = image; ???} ???public String[] getRegions() { ???????return regions; ???} ???public void setRegions(String[] regions) { ???????this.regions = regions; ???} ???public int getNumberSold() { ???????return numberSold; ???} ???public void setNumberSold(int numberSold) { ???????this.numberSold = numberSold; ???}}

package com.cfh.study.lucence_test6;import org.apache.lucene.search.suggest.InputIterator;import org.apache.lucene.util.BytesRef;import java.io.ByteArrayOutputStream;import java.io.IOException;import java.io.ObjectOutputStream;import java.io.UnsupportedEncodingException;import java.util.Comparator;import java.util.HashSet;import java.util.Iterator;import java.util.Set;/** * @Author: cfh * @Date: 2018/9/17 10:21 * @Description: 这个类是核心，决定了你的索引是如何创建的，决定了最终返回的提示关键词列表数据及其排序 */public class ProductIterator implements InputIterator { ???private Iterator<Product> productIterator; ???private Product currentProduct; ???ProductIterator(Iterator<Product> productIterator) { ???????this.productIterator = productIterator; ???} ???/** ????* 设置是否启用Contexts域 ????* @return ????*/ ???public boolean hasContexts() { ???????return true; ???} ???/** ????* 是否有设置payload信息 ????*/ ???public boolean hasPayloads() { ???????return true; ???} ???public Comparator<BytesRef> getComparator() { ???????return null; ???} ???/** ???* next方法的返回值指定的其实就是就是可能返回给我们的suggest的值的结果集合（LookUpResult.key),这里我们选择了商品名。 ???*/ ???public BytesRef next() { ???????if (productIterator.hasNext()) { ???????????currentProduct = productIterator.next(); ???????????try { ???????????????//返回当前Project的name值，把product类的name属性值作为key ???????????????return new BytesRef(currentProduct.getName().getBytes("UTF8")); ???????????} catch (UnsupportedEncodingException e) { ???????????????throw new RuntimeException("Couldn‘t convert to UTF-8",e); ???????????} ???????} else { ???????????return null; ???????} ???} ???/** ????* 将Product对象序列化存入payload ????* [这里仅仅是个示例，其实这种做法不可取,一般不会把整个对象存入payload,这样索引体积会很大，浪费硬盘空间] ????*/ ???public BytesRef payload() { ???????try { ???????????ByteArrayOutputStream bos = new ByteArrayOutputStream(); ???????????ObjectOutputStream out = new ObjectOutputStream(bos); ???????????out.writeObject(currentProduct); ???????????out.close(); ???????????return new BytesRef(bos.toByteArray()); ???????} catch (IOException e) { ???????????throw new RuntimeException("Well that‘s unfortunate."); ???????} ???} ???/** ????* 把产品的销售区域存入context，context里可以是任意的自定义数据，一般用于数据过滤 ????* Set集合里的每一个元素都会被创建一个TermQuery，你只是提供一个Set集合，至于new TermQuery ????* Lucene底层API去做了，但你必须要了解底层干了些什么 ????*/ ???public Set<BytesRef> contexts() { ???????try { ???????????Set<BytesRef> regions = new HashSet<BytesRef>(); ???????????for (String region : currentProduct.getRegions()) { ???????????????regions.add(new BytesRef(region.getBytes("UTF8"))); ???????????} ???????????return regions; ???????} catch (UnsupportedEncodingException e) { ???????????throw new RuntimeException("Couldn‘t convert to UTF-8"); ???????} ???} ???/** ????* 返回权重值，这个值会影响排序 ????* 这里以产品的销售量作为权重值，weight值即最终返回的热词列表里每个热词的权重值 ????* 怎么设计返回这个权重值，发挥你们的想象力吧 ????*/ ???public long weight() { ???????return currentProduct.getNumberSold(); ???}}

private static void lookup(AnalyzingInfixSuggester suggester, String name, ??????????????????????????????String region) throws IOException { ???????HashSet<BytesRef> contexts = new HashSet<BytesRef>(); ???????//先根据region域进行suggest再根据name域进行suggest ???????contexts.add(new BytesRef(region.getBytes("UTF8"))); ???????//num决定了返回几条数据，参数四表明是否所有TermQuery是否都需要满足，参数五表明是否需要高亮显示 ???????List<Lookup.LookupResult> results = suggester.lookup(name, contexts, 2, true, false); ???????System.out.println("-- \"" + name + "\" (" + region + "):"); ???????for (Lookup.LookupResult result : results) { ???????????System.out.println(result.key);//result.key中存储的是根据用户输入内部算法进行匹配后返回的suggest内容 ???????????//从载荷（payload）中反序列化出Product对象(实际生产中出于降低内存占用考虑一般不会在载荷中存储这么多内容) ???????????BytesRef bytesRef = result.payload; ???????????ObjectInputStream is = new ObjectInputStream(new ByteArrayInputStream(bytesRef.bytes)); ???????????Product product = null; ???????????try { ???????????????product = (Product)is.readObject(); ???????????} catch (ClassNotFoundException e) { ???????????????// TODO Auto-generated catch block ???????????????e.printStackTrace(); ???????????} ???????????System.out.println("product-Name:" + product.getName()); ???????????System.out.println("product-regions:" + product.getRegions()); ???????????System.out.println("product-image:" + product.getImage()); ???????????System.out.println("product-numberSold:" + product.getNumberSold()); ???????} ???????System.out.println(); ???}