# Elastic search grouping solution
# As at present ElasticSearch does not provide a group_by equivalent, here's my attempt to do it manually.
# In the example we have articles made by some authors and I'd like to have relevant docs, but not more than one per author.
# Assumption.
# 
# 1) I'm looking for relevant content
# 2) I've assumed that first 300 docs are relevant,
#    So I consider only this selection, regardless many of these are from the same few authors.
# 3) for my needs I didn't "really" needed pagination, for me it was enough a "show more" button updated through ajax

`curl -X DELETE "http://localhost:9200/articles"
 
curl -X PUT    "http://localhost:9200/articles" -d '{
  "settings": {
    "index": {
      "number_of_shards": 1, "number_of_replicas": 0
    }
  }
}'
 
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 111, "author_id": "user_1", "title": "One bad doc", "findable": true }'
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 222, "author_id": "user_2", "title": "Two bad doc", "findable": true }'
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 333, "author_id": "user_3", "title": "Three good doc", "findable": true }'
 
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 444, "author_id": "user_1", "title": "Four good doc", "findable": true }'
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 555, "author_id": "user_2", "title": "Five good doc", "findable": true }'
curl -X POST "http://localhost:9200/articles/article" -d '{ "id": 666, "author_id": "user_1", "title": "Six good doc", "findable": true }'
 
 
curl -XPOST 'http://localhost:9200/articles/_refresh'`

# # Raw test our query
#
# curl -X POST "http://localhost:9200/articles/_search?pretty=true" -d '{
#   "query": {
#       "bool":{
#          "must":[{ "query_string":{ "query":"doc", "default_operator":"AND" } }],
#          "should":[{ "query_string":{ "query":"user_2", "default_operator":"AND", "boost":2000 } }]
#       }
#     },
#   "fields": [{ "term": { findable: "true" } }],
#   "facets": {
#     "tags": { "terms": {"field": "owner", "size": 10} }
#   }
# }'

params_start_from = 0
per_page = 3

my_query = {
    bool: {
       must: [{ query_string: { query: "doc", default_operator: "AND" } }],
       should: [{ query_string: { query: "user_2", default_operator: "AND", boost: 2000 } }]
    }
}
my_and_filters = [
  { term: { findable: "true" } }
]
 
# FIRST QUERY - find all relevant ids
all_res = Tire.search 'articles', query: my_query,
      filter: { :and => my_and_filters },
      fields: ['id', 'author_id'],
      size: 300
 
docs = all_res.results.to_a.uniq { |el| el['author_id'] }
@total_results_non_unique = all_res.results.total # <-- Global variable
@total_results = docs.size # <-- Global variable
 
# PAGINATION
start_from = params_start_from.to_i # should always be < Settings.research.max_results
docs = docs[ start_from .. start_from + per_page - 1 ]
doc_ids = docs.nil? ? [] : docs.map { |doc| doc['id'] }
 
# SECOND QUERY, FIND BY ID
and_filters << { ids: { values: doc_ids } } # TODO: move :highlight to Part 1 and query only by :id
 
res = Tire.search 'articles', query: my_query, 
      filter: { :and => my_and_filters },
      highlight: {
        fields: ['title']
      },
      size: per_page