我确定有人想要这个,所以我会很容易找到。
仅供参考 - 这是在与全新 ES 实例相同的服务器上使用 Node.js(本质上作为批处理脚本)。在 2 个文件上运行它,每个文件有 4000 个项目,在我的共享虚拟服务器上只用了大约 12 秒。 YMMV
var elasticsearch = require('elasticsearch'),
fs = require('fs'),
pubs = JSON.parse(fs.readFileSync(__dirname + '/pubs.json')), // name of my first file to parse
forms = JSON.parse(fs.readFileSync(__dirname + '/forms.json')); // and the second set
var client = new elasticsearch.Client({ // default is fine for me, change as you see fit
host: 'localhost:9200',
log: 'trace'
});
for (var i = 0; i < pubs.length; i++ ) {
client.create({
index: "epubs", // name your index
type: "pub", // describe the data thats getting created
id: i, // increment ID every iteration - I already sorted mine but not a requirement
body: pubs[i] // *** THIS ASSUMES YOUR DATA FILE IS FORMATTED LIKE SO: [{prop: val, prop2: val2}, {prop:...}, {prop:...}] - I converted mine from a CSV so pubs[i] is the current object {prop:..., prop2:...}
}, function(error, response) {
if (error) {
console.error(error);
return;
}
else {
console.log(response); // I don't recommend this but I like having my console flooded with stuff. It looks cool. Like I'm compiling a kernel really fast.
}
});
}
for (var a = 0; a < forms.length; a++ ) { // Same stuff here, just slight changes in type and variables
client.create({
index: "epubs",
type: "form",
id: a,
body: forms[a]
}, function(error, response) {
if (error) {
console.error(error);
return;
}
else {
console.log(response);
}
});
}
希望我能帮助的不仅仅是我自己。不是火箭科学,但可能会为某人节省 10 分钟。
干杯