织梦dedecms大气微电影网站模板网站模板及源码
前言
MongoDB区别Mysql的地方，就是MongoDB支持文档嵌套，比如最近业务中就有一个在音频转写结果中进行对话场景，一个音频中对应多轮对话，这些音频数据和对话信息就存储在MongoDB中文档中。集合结构大致如下
{"_id":23424234234324234,"audioId": 2689944,"contextId": "cht000d24ab@dx187d1168a449a4b540","dialogues": [{"ask": "今天是礼拜天？","answer": "是的","createTime": 1697356990966}, {"ask": "你也要加油哈","answer": "奥利给！","createTime": 1697378011483}, {"ask": "下周见","answer": "拜拜！","createTime": 1697378072063}]
}下面简单介绍几个业务中用到的简单操作。
查询嵌套List的长度大小
public Integer getDialoguesSize(Long audioId) {Integer datasSize = 0;List<Document> group = Arrays.asList(new Document("$match",new Document("audioId",new Document("$eq", audioId))), new Document("$match",new Document("dialogues",new Document("$exists", true))), new Document("$project",new Document("datasSize",new Document("$size", "$dialogues"))));AggregateIterable<Document> aggregate = generalCollection.aggregate(group);Document document = aggregate.first();if (document != null) {datasSize = (Integer) document.get("datasSize");}return datasSize;}根据嵌套List中属性查询
下面的代码主要查询指定audioId中的dialogues集合中小于createTime,并且根据limit分页查询，这里用到了MongoDB中的Aggregates和unwind来进行聚合查询,具体使用细节，可以参见MongoDB官方文档
public AIDialoguesResultDTO queryAiResult(Long audioId, Long createTime, Integer limit) {AIDialoguesResultDTO aiDialoguesResultDTO = new AIDialoguesResultDTO();List<Bson> pipeline = Arrays.asList(Aggregates.match(Filters.eq("audioId", audioId)),Aggregates.unwind("$dialogues"),Aggregates.match(Filters.lt("dialogues.createTime", createTime)),Aggregates.sort(Sorts.descending("dialogues.createTime")),Aggregates.limit(limit));AggregateIterable<Document> aggregate = generalCollection.aggregate(pipeline);List<AIDialoguesResult> aiDialoguesResultList = new ArrayList<>();String contextId = Constant.EMPTY_STR;for (Document document : aggregate) {AIDialoguesResult aiDialoguesResult = new AIDialoguesResult();List<String> key = Collections.singletonList("dialogues");aiDialoguesResult.setAnswer(document.getEmbedded(key, Document.class).getString("answer"));aiDialoguesResult.setAsk(document.getEmbedded(key, Document.class).getString("ask"));aiDialoguesResult.setCreateTime(document.getEmbedded(key, Document.class).getLong("createTime"));aiDialoguesResultList.add(aiDialoguesResult);contextId = document.getString("contextId");}if (!CollectionUtils.isEmpty(aiDialoguesResultList)) {aiDialoguesResultList = aiDialoguesResultList.stream().sorted(Comparator.comparingLong(AIDialoguesResult::getCreateTime)).collect(Collectors.toList());}aiDialoguesResultDTO.setCount(aiDialoguesResultList.size());aiDialoguesResultDTO.setContextId(contextId);aiDialoguesResultDTO.setResult(aiDialoguesResultList);return aiDialoguesResultDTO;}当然，我们还有一种比较简单的写法
public AIDialoguesResultDTO queryAiResultBackupVersion(Long audioId, Long createTime, Integer limit) {Bson query = and(eq("audioId", audioId));AITextResult aiTextResult = mongoDao.findSingle(query, AITextResult.class);AIDialoguesResultDTO aiDialoguesResultDTO = new AIDialoguesResultDTO();if (Objects.isNull(aiTextResult)) {aiDialoguesResultDTO.setResult(Collections.emptyList());aiDialoguesResultDTO.setCount(0);aiDialoguesResultDTO.setContextId("");}List<AIDialoguesResult> aiDialoguesResultList = aiTextResult.getDialogues();if (CollectionUtils.isEmpty(aiDialoguesResultList)) {return aiDialoguesResultDTO;}Long finalCreateTime = createTime;List<AIDialoguesResult> afterFilterAiDialoguesResultList =aiDialoguesResultList.stream().filter(t -> t.getCreateTime()< finalCreateTime).sorted(Comparator.comparingLong(AIDialoguesResult::getCreateTime).reversed()).limit(limit).collect(Collectors.toList());if (CollectionUtils.isEmpty(afterFilterAiDialoguesResultList)) {aiDialoguesResultDTO.setCount(0);} else {aiDialoguesResultDTO.setCount(afterFilterAiDialoguesResultList.size());}afterFilterAiDialoguesResultList = afterFilterAiDialoguesResultList.stream().sorted(Comparator.comparingLong(AIDialoguesResult::getCreateTime)).collect(Collectors.toList());aiDialoguesResultDTO.setResult(afterFilterAiDialoguesResultList);aiDialoguesResultDTO.setContextId(aiTextResult.getContextId());return aiDialoguesResultDTO;}上面这种写法比较直接，就是直接audioId进行匹配查询， 然后将当前文档中的dialogues全部加载到内存中，然后在内存中进行排序，分页返回，显然如果dialogues集合长度很大，对内存占用会比较高。
嵌套List的增量追加
对于dialogues数组，如果我们要向dialogues追加元素，我们可以把audioId对应的dialogues全部取出来，然后在List后面追加一个元素，大致代码如下
public void saveAiResult(SaveAIResultDTO saveAIResultDTO) {Long audioId = saveAIResultDTO.getAudioId();Bson filter = Filters.eq("audioId", audioId);AITextResult aiTextResult = mongoDao.findSingle(filter, AITextResult.class);if (Objects.isNull(aiTextResult)) {aiTextResult = AITextResult.buildAiTextResult(saveAIResultDTO);mongoDao.saveOrUpdate(aiTextResult);return;}List<AIDialoguesResult> aiDialoguesResults = aiTextResult.getDialogues();AIDialoguesResult aiDialoguesResult = new AIDialoguesResult();aiDialoguesResult.setCreateTime(new Date().getTime());aiDialoguesResult.setAsk(saveAIResultDTO.getAsk());aiDialoguesResult.setAnswer(saveAIResultDTO.getAnswer());aiDialoguesResults.add(aiDialoguesResult);aiTextResult.setDialogues(aiDialoguesResults);mongoDao.saveOrUpdate(aiTextResult);}上面这种写法本身没有什么问题，但是如果dialogues集合大小比较大，每次追加都将dialogues全部取出来进行追加操作，可能比较占用内存，我们可以利用MongoDB中的push操作，直接追加
public void saveAiResultIncremental(SaveAIResultDTO saveAIResultDTO) {Long audioId = saveAIResultDTO.getAudioId();Document query = new Document("audioId", audioId);Bson projection = Projections.fields(Projections.include("contextId"), Projections.excludeId());FindIterable<Document> result = generalCollection.find(query).projection(projection);AITextResult aiTextResult;if (!result.iterator().hasNext()) {aiTextResult = AITextResult.buildAiTextResult(saveAIResultDTO);mongoDao.saveOrUpdate(aiTextResult);return;}AIDialoguesResult aiDialoguesResult = new AIDialoguesResult();aiDialoguesResult.setCreateTime(new Date().getTime());aiDialoguesResult.setAsk(saveAIResultDTO.getAsk());aiDialoguesResult.setAnswer(saveAIResultDTO.getAnswer());Bson update = push("dialogues", aiDialoguesResult);Bson filter = Filters.eq("audioId", audioId);generalCollection.updateOne(filter, update);}总结
既然选择了MongoDB,就不能继续沿用Mysql的查询风格，要学会利用MongoDB的特性，否则往往达不到预期效果。