我正在尝试在使用elasticsearch的应用程序中支持smart-case search。我想支持的用例是能够使用智能案例语义部分匹配任何文本blob。我设法以这样的方式配置我的索引，以便我能够模拟智能案例搜索。它使用最大长度为8的ngram，不会超出存储要求。
它的工作方式是每个文档都使用case-sensitive生成的case-insensitive和copy_to字段，并使用自己的特定索引策略。在搜索给定输入时，我将输入分成几部分。这取决于ngrams长度，空格和双引号转义。检查每个部分的大写字母。找到大写字母后，它会使用区分大小写的字段为该特定部分生成匹配过滤器，否则使用不区分大小写的字段。
事实证明这很有效，但是我很难突出显示工作方式。为了更好地解释这个问题，我在下面添加了对我的测试设置的概述。
curl -X DELETE localhost:9200/custom
curl -X PUT localhost:9200/custom -d '
{
"settings": {
"analysis": {
"filter": {
"default_min_length": {
"type": "length",
"min": 1
},
"squash_spaces": {
"type": "pattern_replace",
"pattern": "\\s{2,}",
"replacement": " "
}
},
"tokenizer": {
"ngram_tokenizer": {
"type": "nGram",
"min_gram": "2",
"max_gram": "8"
}
},
"analyzer": {
"index_raw": {
"type": "custom",
"filter": ["lowercase","squash_spaces","trim","default_min_length"],
"tokenizer": "keyword"
},
"index_case_insensitive": {
"type": "custom",
"filter": ["lowercase","squash_spaces","trim","default_min_length"],
"tokenizer": "ngram_tokenizer"
},
"search_case_insensitive": {
"type": "custom",
"filter": ["lowercase","squash_spaces","trim"],
"tokenizer": "keyword"
},
"index_case_sensitive": {
"type": "custom",
"filter": ["squash_spaces","trim","default_min_length"],
"tokenizer": "ngram_tokenizer"
},
"search_case_sensitive": {
"type": "custom",
"filter": ["squash_spaces","trim"],
"tokenizer": "keyword"
}
}
}
},
"mappings": {
"_default_": {
"_all": { "enabled": false },
"date_detection": false,
"dynamic_templates": [
{
"case_insensitive": {
"match_mapping_type": "string",
"match": "case_insensitive",
"mapping": {
"type": "string",
"analyzer": "index_case_insensitive",
"search_analyzer": "search_case_insensitive"
}
}
},
{
"case_sensitive": {
"match_mapping_type": "string",
"match": "case_sensitive",
"mapping": {
"type": "string",
"analyzer": "index_case_sensitive",
"search_analyzer": "search_case_sensitive"
}
}
},
{
"text": {
"match_mapping_type": "string",
"mapping": {
"type": "string",
"analyzer": "index_raw",
"copy_to": ["case_insensitive","case_sensitive"],
"fields": {
"case_insensitive": {
"type": "string",
"analyzer": "index_case_insensitive",
"search_analyzer": "search_case_insensitive",
"term_vector": "with_positions_offsets"
},
"case_sensitive": {
"type": "string",
"analyzer": "index_case_sensitive",
"search_analyzer": "search_case_sensitive",
"term_vector": "with_positions_offsets"
}
}
}
}
}
]
}
}
}
'
curl -X POST "http://localhost:9200/custom/test" -d '{ "text" : "tHis .is a! Test" }'
用户搜索：tHis test，它被分成两部分，因为ngrams的长度最多为8个：（1）tHis和（2）test。对于（1），使用区分大小写的字段，（2）使用不区分大小写的字段。
curl -X POST "http://localhost:9200/_search" -d '
{
"size": 1,
"query": {
"bool": {
"must": [
{
"match": {
"case_sensitive": {
"query": "tHis",
"type": "boolean"
}
}
},
{
"match": {
"case_insensitive": {
"query": "test",
"type": "boolean"
}
}
}
]
}
},
"highlight": {
"pre_tags": [
"<em>"
],
"post_tags": [
"</em>"
],
"number_of_fragments": 0,
"require_field_match": false,
"fields": {
"*": {}
}
}
}
'
{
"took": 10,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 1,
"max_score": 0.057534896,
"hits": [
{
"_index": "custom",
"_type": "test",
"_id": "1",
"_score": 0.057534896,
"_source": {
"text": "tHis .is a! Test"
},
"highlight": {
"text.case_sensitive": [
"<em>tHis</em> .is a! Test"
],
"text.case_insensitive": [
"tHis .is a!<em> Test</em>"
]
}
}
]
}
}
如您所见，响应显示智能案例搜索效果非常好。但是，我还想使用突出显示给用户反馈。我当前的设置使用"term_vector": "with_positions_offsets"生成突出显示。这确实给出了正确的亮点。但是，高亮显示区分为区分大小写且不区分大小写。
"highlight": {
"text.case_sensitive": [
"<em>tHis</em> .is a! Test"
],
"text.case_insensitive": [
"tHis .is a!<em> Test</em>"
]
}
这需要我将同一字段上的多个高光手动压缩成一个组合高光，然后再将其返回给用户。当高光变得更复杂并且可能重叠时，这变得非常痛苦。
是否有其他设置可以实际取回组合的高光。即我希望将此作为我回复的一部分。
"highlight": {
"text": [
"<em>tHis</em> .is a!<em> Test</em>"
]
}
答案 0 :(得分：1)
利用突出显示查询来获得合并结果：
curl -XPOST 'http://localhost:9200_search' -d '
{
"size": 1,
"query": {
"bool": {
"must": [
{
"match": {
"case_sensitive": {
"query": "tHis",
"type": "boolean"
}
}
},
{
"match": {
"case_insensitive": {
"query": "test",
"type": "boolean"
}
}
}
]
}
},
"highlight": {
"pre_tags": [
"<em>"
],
"post_tags": [
"</em>"
],
"number_of_fragments": 0,
"require_field_match": false,
"fields": {
"*.case_insensitive": {
"highlight_query": {
"bool": {
"must": [
{
"match": {
"*.case_insensitive": {
"query": "tHis",
"type": "boolean"
}
}
},
{
"match": {
"*.case_insensitive": {
"query": "test",
"type": "boolean"
}
}
}
]
}
}
}
}
}
}
'
{
"took": 5,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 1,
"max_score": 0.9364339,
"hits": [
{
"_index": "custom",
"_type": "test",
"_id": "1",
"_score": 0.9364339,
"_source": {
"text": "tHis .is a! Test"
},
"highlight": {
"text.case_insensitive": [
"<em>tHis</em> .is a!<em> Test</em>"
]
}
}
]
}
}
在提取以下内容时，请注意其他小写test关键字：
curl -X POST "http://localhost:9200/custom/test" -d '{ "text" : "tHis this .is a! Test" }'
对同一查询的响应变为：
{
"took": 5,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 1,
"max_score": 0.9364339,
"hits": [
{
"_index": "custom",
"_type": "test",
"_id": "1",
"_score": 0.9364339,
"_source": {
"text": "tHis this .is a! Test"
},
"highlight": {
"text.case_insensitive": [
"<em>tHis</em><em> this</em> .is a!<em> Test</em>"
]
}
}
]
}
}
如您所见，突出显示现在还包括小写this。对于这样的测试示例，我们不介意。但是，对于复杂的查询，用户可能（并且可能会）对智能案例何时以及如何产生影响感到困惑。特别是当小写匹配包含仅匹配小写的字段时。
此解决方案将为您提供合并为一个的所有突出显示，但可能包含不需要的结果。