这段代码展示了如何使用 Elasticsearch 的 Java API 进行索引管理和文档操作，包括检查索引是否存在、创建和删除索引、按ID查找和更新文档，以及进行分词查询和高亮显示。此外，还提供了批量导入数据的方法。
先把需要用的类注入进来
这两个类在meaven导入的时候就注入到spring了
@Autowired
private TransportClient transportClient;
private static TransportClient client;
根据ID查找elasticsearch是否存在某条数据
/**
* 指定ID，查询数据
* @param index
* @param type
* @param id
* @param fields 需要显示的字段，逗号分隔（缺省为全部字段）
* @return
*/
public static Map<String,Object> searchDataById(String index, String type, String id, String fields) {
GetRequestBuilder getRequestBuilder = client.prepareGet(index, type, id);
if (StringUtils.isNotEmpty(fields)) {
getRequestBuilder.setFetchSource(fields.split(","), null);
}
GetResponse getResponse = getRequestBuilder.execute().actionGet();
return getResponse.getSource();
}
判断索引是否存在
/**
* 判断索引是否存在
* @param index
* @return
*/
public static boolean isIndexExist(String index) {
IndicesExistsResponse inExistsResponse = client.admin().indices()
.exists(new IndicesExistsRequest(index)).actionGet();
if(inExistsResponse.isExists()) {
System.out.println("索引 "+ index + " 已存在。");
}
else {
System.out.println("索引 "+ index + " 不存在。");
}
return inExistsResponse.isExists();
}
创建索引
/**
* 创建索引
* @param index
* @return
*/
public static boolean createIndex(String index) {
if(!isIndexExist(index)) {
CreateIndexResponse indexResponse = client.admin().indices().prepareCreate(index).execute().actionGet();
if(indexResponse.isAcknowledged()) {
System.out.println("索引 "+ index + " 创建成功。");
}
else {
System.out.println("索引 "+ index + " 创建失败。");
}
return indexResponse.isAcknowledged();
}
return false;
}
删除索引
/**
* 删除索引
* @param index
* @return
*/
public static boolean deleteIndex(String index) {
if(isIndexExist(index)) {
AcknowledgedResponse dResponse = client.admin().indices().prepareDelete(index).execute().actionGet();
if (dResponse.isAcknowledged()) {
System.out.println("索引 "+ index + " 删除成功。");
} else {
System.out.println("索引 "+ index + " 删除失败。");
}
return dResponse.isAcknowledged();
}
else {
return false;
}
}
指定ID添加文档
/**
* 指定ID，添加文档(单条数据)
* @param jsonObject
* @param index
* @param type
* @param id
* @return
*/
public static String addData(JSONObject jsonObject, String index, String type, String id) {
IndexResponse response = client.prepareIndex(index, type, id).setSource(jsonObject).get();
System.out.println("添加数据状况: "+ response.status().getStatus() +" 。");
return response.getId();
}
其余的
/**
* 指定ID，删除文档(单条数据)
* @param index
* @param type
* @param id
*/
public static void deleteDataById(String index, String type, String id) {
DeleteResponse response = client.prepareDelete(index, type, id).execute().actionGet();
System.out.println("删除数据状况: "+ response.status().getStatus() +" 。");
}
/**
* 指定ID，更新文档(单条数据)
* @param jsonObject
* @param index
* @param type
* @param id
*/
public static void updateDataById(JSONObject jsonObject, String index, String type, String id) {
UpdateRequest updateRequest = new UpdateRequest();
updateRequest.index(index).type(type).id(id).doc(jsonObject);
client.update(updateRequest);
}
/**
* 指定ID，查询数据
* @param index
* @param type
* @param id
* @param fields 需要显示的字段，逗号分隔（缺省为全部字段）
* @return
*/
public static Map<String,Object> searchDataById(String index, String type, String id, String fields) {
GetRequestBuilder getRequestBuilder = client.prepareGet(index, type, id);
if (StringUtils.isNotEmpty(fields)) {
getRequestBuilder.setFetchSource(fields.split(","), null);
}
GetResponse getResponse = getRequestBuilder.execute().actionGet();
return getResponse.getSource();
}
/**
* 分词查询，并高亮
*
* @param index
* @param type
* @param query 查询条件
* @param size 文档大小限制
* @param fields 需要显示的字段，逗号分隔（缺省为全部字段）
* @param sortField 排序字段
* @param highlightField 高亮字段
* @return
*/
public static Map<String, Object> searchListData(String index, String type, QueryBuilder query, Integer size, String fields, String sortField, String highlightField) {
SearchRequestBuilder searchRequestBuilder = client.prepareSearch(index);
if (StringUtils.isNotEmpty(type)) {
searchRequestBuilder.setTypes(type.split(","));
}
//设置查询条件
searchRequestBuilder.setQuery(query);
//需要显示的字段，逗号分隔（缺省为全部字段）
if (StringUtils.isNotEmpty(fields)) {
searchRequestBuilder.setFetchSource(fields.split(","), null);
}
searchRequestBuilder.setFetchSource(true);
//设置是否按查询匹配度排序
searchRequestBuilder.setExplain(true);
//排序字段
// if (StringUtils.isNotEmpty(sortField)) {
// searchRequestBuilder.addSort(sortField, SortOrder.DESC);
// }
//设置高亮
if (StringUtils.isNotEmpty(highlightField)) {
HighlightBuilder highlightBuilder = new HighlightBuilder();
String[] highlightFields = highlightField.split(",");
for(String hField: highlightFields) {
highlightBuilder.field(new HighlightBuilder.Field(hField));
}
highlightBuilder.preTags("<span style='color:red'>");//设置前缀
highlightBuilder.postTags("</span>");//设置后缀
highlightBuilder.fragmentSize(800000); //最大高亮分片数
highlightBuilder.numOfFragments(0);
searchRequestBuilder.highlighter(highlightBuilder);
}
if (size != null && size > 0) {
searchRequestBuilder.setSize(size);
}
//打印的内容,可以在 Elasticsearch head 和 Kibana 上执行查询
System.out.println(searchRequestBuilder);
SearchResponse searchResponse = searchRequestBuilder.execute().actionGet();
long total = searchResponse.getHits().totalHits;
long length = searchResponse.getHits().getHits().length;
System.out.println("共查询到" + total + "条数据,处理数据条数为" + length +"条。");
if (searchResponse.status().getStatus() == 200) {
// List<Map<String, Object>> sourceList = new ArrayList<Map<String, Object>>();
// for (SearchHit searchHit : searchResponse.getHits().getHits()) {
// sourceList.add(searchHit.getSourceAsMap());
// }
// return sourceList;
//实现高亮
List<Map<String, Object>> sourceList = setSearchResponse(searchResponse, highlightField);
Map<String, Object> map = new HashMap<String, Object>();
map.put("total", total);
map.put("sourceList", sourceList);
return map;
}
return null;
}
/**
* 分词查询，并分页、高亮
*
* @param index
* @param type
* @param startPage 当前页
* @param pageSize 每页显示条数
* @param query 查询条件
* @param fields 需要显示的字段，逗号分隔（缺省为全部字段）
* @param sortField 排序字段
* @param highlightField 高亮字段
* @return
*/
public static Map<String, Object> searchListDataPage(String index, String type, int startPage, int pageSize, QueryBuilder query, String fields, String sortField, String highlightField) {
SearchRequestBuilder searchRequestBuilder = client.prepareSearch(index);
if (StringUtils.isNotEmpty(type)) {
searchRequestBuilder.setTypes(type.split(","));
}
searchRequestBuilder.setSearchType(SearchType.QUERY_THEN_FETCH);
//需要显示的字段，逗号分隔（缺省为全部字段）
if (StringUtils.isNotEmpty(fields)) {
searchRequestBuilder.setFetchSource(fields.split(","), null);
}
//排序字段
if (StringUtils.isNotEmpty(sortField)) {
searchRequestBuilder.addSort(sortField, SortOrder.DESC);
}
//设置高亮
if (StringUtils.isNotEmpty(highlightField)) {
HighlightBuilder highlightBuilder = new HighlightBuilder();
String[] highlightFields = highlightField.split(",");
for(String hField: highlightFields) {
highlightBuilder.field(new HighlightBuilder.Field(hField));
}
// 设置高亮字段
// HighlightBuilder.Field highlightTitle = new HighlightBuilder.Field("title");
// highlightBuilder.field(highlightTitle);
//
// HighlightBuilder.Field highlightDetail = new HighlightBuilder.Field("details");
// highlightBuilder.field(highlightDetail);
highlightBuilder.preTags("<span style='color:red'>");//设置前缀
highlightBuilder.postTags("</span>");//设置后缀
highlightBuilder.fragmentSize(800000); //最大高亮分片数
highlightBuilder.numOfFragments(0);
searchRequestBuilder.highlighter(highlightBuilder);
}
//设置查询条件
searchRequestBuilder.setQuery(query);
//分页应用
searchRequestBuilder.setFrom((startPage-1)*pageSize).setSize(pageSize);
//设置是否按查询匹配度排序
searchRequestBuilder.setExplain(true);
//打印的内容,可以在 Elasticsearch head 和 Kibana 上执行查询
System.out.println(searchRequestBuilder);
SearchResponse searchResponse = searchRequestBuilder.execute().actionGet();
long total = searchResponse.getHits().totalHits;
long length = searchResponse.getHits().getHits().length;
System.out.println("共查询到" + total + "条数据,处理数据条数为" + length +"条。");
if (searchResponse.status().getStatus() == 200) {
// List<Map<String, Object>> sourceList = new ArrayList<Map<String, Object>>();
// for (SearchHit searchHit : searchResponse.getHits().getHits()) {
// sourceList.add(searchHit.getSourceAsMap());
// }
//实现高亮
List<Map<String, Object>> sourceList = setSearchResponse(searchResponse, highlightField);
Map<String, Object> map = new HashMap<String, Object>();
map.put("total", total);
map.put("sourceList", sourceList);
return map;
}
return null;
}
/**
* 批量导入所有文档（不是部分更新），该代码不能共用，只适用于“ESKnowledgeEntity”
* 先删除索引（原来所有数据），再添加数据
* @param know_list
* @param index
* @param type
*/
public static void addAllData(List<ESKnowledgeEntity> know_list, String index, String type) {
//删除索引（删除索引的时候，会去判断该索引是否存在）
deleteIndex(index);
//detail内容有大量的html标签，去除html标签
know_list.forEach(esKnowledgeEntity -> {
esKnowledgeEntity.setDetails(delHTMLTag(esKnowledgeEntity.getDetails()));
});
//建立批量提交类
BulkRequestBuilder bulkRequest= client.prepareBulk();
for(ESKnowledgeEntity know: know_list) {
//将实体类直接转为JSON字符串
String source = JSONSerializer.toJSON(know).toString();
bulkRequest.add(client.prepareIndex(index,type,know.getRecId()).setSource(source,XContentType.JSON));
}
bulkRequest.execute().actionGet();
System.out.println("共查询到" + know_list.size() + "条数据,已导入成功");
}
/**
* 批量导入部分文档，该代码不能共用，只适用于“ESKnowledgeEntity”
* 无需删除原有文档，已存在的文档将更新，不存在的文档选择插入
* @param know_list
* @param index
* @param type
*/
public static boolean addListData(List<ESKnowledgeEntity> know_list, String index, String type) {
//和以上方法同样，该导入方法也必须判断当前索引是否存在
boolean flag = false;
int count = 0;
if(isIndexExist(index)) {
//detail内容有大量的html标签，去除html标签
know_list.forEach(esKnowledgeEntity -> {
esKnowledgeEntity.setDetails(delHTMLTag(esKnowledgeEntity.getDetails()));
});
for(ESKnowledgeEntity know: know_list) {
//将实体类直接转为JSON字符串,再转为JSONObject
String source = JSONSerializer.toJSON(know).toString();
JSONObject json = JSONObject.parseObject(source);
//查询相应ID的数据，判断是否已存在
Map<String,Object> map = searchDataById(index, type, know.getRecId(), null);
//存在就更新，不存在就插入
if(map!=null) {
updateDataById(json, index, type, know.getRecId());
}
else {
addData(json, index, type, know.getRecId());
}
count++;
}
System.out.println("共查询到" + count + "条数据,已导入成功");
flag = true;
return flag;
}
return flag;
}
/**
* 去除details中html标签
* @param htmlStr
* @return
*/
public static String delHTMLTag(String htmlStr) {
String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
Matcher m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //过滤style标签
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //过滤html标签
// htmlStr = htmlStr.replace(" ", "");
// htmlStr = htmlStr.replaceAll("\\s*|\t|\r|\n", "");
// htmlStr = htmlStr.replace("“", "");
// htmlStr = htmlStr.replace("”", "");
// htmlStr = htmlStr.replaceAll(" ", "");
htmlStr = htmlStr.replace(" ", "");
return htmlStr.trim(); //返回文本字符串
}
/**
* 高亮处理
* @param searchResponse
* @param highlightField
* @return
*/
private static List<Map<String, Object>> setSearchResponse(SearchResponse searchResponse, String highlightField) {
List<Map<String, Object>> sourceList = new ArrayList<Map<String, Object>>();
StringBuffer stringBuffer = new StringBuffer();
String[] hFields = highlightField.split(",");
for (SearchHit searchHit : searchResponse.getHits().getHits()) {
searchHit.getSourceAsMap().put("id", searchHit.getId());
for(String hFiled:hFields) {
highlightField = hFiled;
if (StringUtils.isNotEmpty(highlightField)) {
stringBuffer = new StringBuffer();
//System.out.println("遍历 高亮结果集，覆盖 正常结果集" + searchHit.getSourceAsMap());
Map<String, HighlightField> highlightFields = searchHit.getHighlightFields();
if(highlightFields.containsKey(highlightField)) {
Text[] text = searchHit.getHighlightFields().get(highlightField).getFragments();
if (text != null) {
for (Text str : text) {
stringBuffer.append(str.string());
}
//遍历 高亮结果集，覆盖 正常结果集
searchHit.getSourceAsMap().put(highlightField, stringBuffer.toString());
}
}
}
}
sourceList.add(searchHit.getSourceAsMap());
}
return sourceList;
}
3082
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
