我正在尝试通过从" 匹配"文档中获取一些元素来丰富我的搜索结果"喜欢
<options xmlns="http://marklogic.com/appservices/search">
<extract-document-data selected="include">
<extract-path>/language-version/language-version-canonical-model/title</extract-path>
<extract-path>/language-version/language-version-canonical-model/language</extract-path>
</extract-document-data>
(...)
</options>
当我运行搜索时,我要求JSON输出(使用标题接受:application/json
),我会作为 JSON 和" strinxml >"的混合。
{
"snippet-format": "snippet",
"total": 564,
"start": 1,
"page-length": 10,
"selected": "include",
"results": [
{
"index": 1,
"uri": "ENV/CHEM/NANO(2015)22/ANN5/2",
"path": "fn:doc("ENV/CHEM/NANO(2015)22/ANN5/2")",
(...)
"matches": [
{
"path": "fn:doc("ENV/CHEM/NANO(2015)22/ANN5/2")/ns2:language-version/ns2:language-version-raw-data/*:document/*:page[22]",
(...)
}
],
"extracted": {
"kind": "element",
"content": [
"<language>En</language>",
"<title>ZINC OXIDE DOSSIERANNEX 5</title>",
"<reference>ENV/CHEM/NANO(2015)22/ANN5</reference>",
"<classification>2</classification>",
"<modificationDate>2015-04-16T00:00:00.000+02:00</modificationDate>",
"<subject label_en="media" >media</subject>",
"<subject label_en="fish" ">fish</subject>",
]
}
},
这里的问题是" 提取"部分,如您所见,看起来 xml 元素已被简单地复制为字符串期望它们转换为 JSON 。
有人对这个问题有想法吗?
标记不会转换内容。因此,在要求JSON格式化的搜索响应时,XML将保留XML。而且,由于您无法真正将XML嵌入JSON中,因此它被序列化为字符串。
您可以尝试在搜索结果上应用REST转换,并使用JSON:Transform-to-Json(可能带有自定义配置)之类的内容即时转换。例如类似此服务器端JavaScript变换的内容:
/* jshint node:true,esnext:true */
/* global xdmp */
var json = require('/MarkLogic/json/json.xqy');
var config = json.config('custom');
function toJson(context, params, content) {
'use strict';
var response = content.toObject();
if (response.results) {
response.results.map(function(result) {
if (result.extracted && result.extracted.content) {
result.extracted.content.map(function(content, index) {
if (content.match(/^</) && !content.match(/^<!/)) {
result.extracted.content[index] = json.transformToJson(xdmp.unquote(content), config);
}
});
}
});
}
return response;
}
exports.transform = toJson;
您当然也可以转换客户端。
hth!
如果您使用的是Java客户端API,则可以为每个结果使用正确的句柄来读取提取的项目(请参阅ExtractedResult和ExtractedEtem):
SearchHandle results = queryManager.search(query, new SearchHandle());
for (MatchDocumentSummary summary : results.getMatchResults()) {
ExtractedResult extracted = summary.getExtracted();
// here we check to see if this result is XML format, and if so
// we use org.w3c.dom.Document
if ( Format.XML == summary.getFormat() ) {
for (ExtractedItem item : extracted) {
Document extractItem = item.getAs(new DOMHandle()).get();
...
}
// or if the result is JSON we could choose a different handle
} else if ( Format.JSON == summary.getFormat() ) {
for (ExtractedItem item : extracted) {
JsonNode extractItem = item.getAs(JsonNode.class);
...
}
}
}