Search: Full text search of Elasticsearch

Description

Full text search of Elasticsearch

Usage

Search(index = NULL, type = NULL, q = NULL, df = NULL, analyzer = NULL, default_operator = NULL, explain = NULL, source = NULL, fields = NULL, sort = NULL, track_scores = NULL, timeout = NULL, terminate_after = NULL, from = NULL, size = NULL, search_type = NULL, lowercase_expanded_terms = NULL, analyze_wildcard = NULL, version = FALSE, lenient = FALSE, body = list(), raw = FALSE, asdf = FALSE, scroll = NULL, search_path = "_search", ...)

Arguments

index

Index name, one or more

type

Document type

The query string (maps to the query_string query, see Query String Query for more details). See https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html for documentation and examples.

(character) The default field to use when no field prefix is defined within the query.

analyzer

(character) The analyzer name to be used when analyzing the query string.

default_operator

(character) The default operator to be used, can be AND or OR. Default: OR

explain

(logical) For each hit, contain an explanation of how scoring of the hits was computed. Default: FALSE

source

(logical) Set to FALSE to disable retrieval of the _source field. You can also retrieve part of the document by using _source_include & _source_exclude (see the body documentation for more details)

fields

(character) The selective stored fields of the document to return for each hit. Not specifying any value will cause no fields to return.

sort

(character) Sorting to perform. Can either be in the form of fieldName, or fieldName:asc/fieldName:desc. The fieldName can either be an actual field within the document, or the special _score name to indicate sorting based on scores. There can be several sort parameters (order is important).

track_scores

(logical) When sorting, set to TRUE in order to still track scores and return them as part of each hit.

timeout

(numeric) A search timeout, bounding the search request to be executed within the specified time value and bail with the hits accumulated up to that point when expired. Default: no timeout.

terminate_after

(numeric) The maximum number of documents to collect for each shard, upon reaching which the query execution will terminate early. If set, the response will have a boolean field terminated_early to indicate whether the query execution has actually terminated_early. Defaults to no terminate_after.

from

(character) The starting from index of the hits to return. Pass in as a character string to avoid problems with large number conversion to scientific notation. Default: 0

size

(character) The number of hits to return. Pass in as a character string to avoid problems with large number conversion to scientific notation. Default: 10. The default maximum is 10,000 - however, you can change this default maximum by changing the index.max_result_window index level parameter.

search_type

(character) The type of the search operation to perform. Can be query_then_fetch (default) or dfs_query_then_fetch. Types scan and count are deprecated. See http://bit.ly/19Am9xP for more details on the different types of search that can be performed.

lowercase_expanded_terms

(logical) Should terms be automatically lowercased or not. Default: TRUE.

analyze_wildcard

(logical) Should wildcard and prefix queries be analyzed or not. Default: FALSE.

version

(logical) Print the document version with each document.

lenient

If TRUE will cause format based failures (like providing text to a numeric field) to be ignored. Default: FALSE

body

Query, either a list or json.

raw

(logical) If FALSE (default), data is parsed to list. If TRUE, then raw JSON returned

asdf

(logical) If TRUE, use fromJSON to parse JSON directly to a data.frame. If FALSE (Default), list output is given.

scroll

(character) Specify how long a consistent view of the index should be maintained for scrolled search, e.g., "30s", "1m". See units-time.

search_path

(character) The path to use for searching. Default to _search, but in some cases you may already have that in the base url set using connect, in which case you can set this to NULL

...

Curl args passed on to POST

Details

This function name has the "S" capitalized to avoid conflict with the function base::search. I hate mixing cases, as I think it confuses users, but in this case it seems neccessary.

References

https://www.elastic.co/guide/en/elasticsearch/reference/current/search-search.html https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html

Examples

Run this code

## Not run: 
# if (!index_exists("shakespeare")) {
#   shakespeare <- system.file("examples", "shakespeare_data.json", package = "elastic")
#   docs_bulk(shakespeare)
# }
# 
# # URI string queries
# Search(index="shakespeare")
# Search(index="shakespeare", type="act")
# Search(index="shakespeare", type="scene")
# Search(index="shakespeare", type="line")
# 
# ## Return certain fields
# Search(index="shakespeare", fields=c('play_name','speaker'))
# 
# ## Search multiple indices
# Search(index = "gbif")$hits$total
# Search(index = "shakespeare")$hits$total
# Search(index = c("gbif", "shakespeare"))$hits$total
# 
# ## search_type
# Search(index="shakespeare", search_type = "query_then_fetch")
# Search(index="shakespeare", search_type = "dfs_query_then_fetch")
# ### search type "scan" is gone - use scroll instead
# Search(index="shakespeare", scroll = "2m")
# ### search type "count" is gone - use size=0 instead
# Search(index="shakespeare", size = 0)$hits$total
# 
# ## search exists check
# ### use size set to 0 and terminate_after set to 1
# ### if there are > 0 hits, then there are matching documents
# Search(index="shakespeare", type="act", size = 0, terminate_after = 1)
# 
# ## sorting
# Search(index="shakespeare", type="act", sort="text_entry")
# Search(index="shakespeare", type="act", sort="speaker:desc", fields='speaker')
# Search(index="shakespeare", type="act",
#  sort=c("speaker:desc","play_name:asc"), fields=c('speaker','play_name'))
# 
# ## paging
# Search(index="shakespeare", size=1, fields='text_entry')$hits$hits
# Search(index="shakespeare", size=1, from=1, fields='text_entry')$hits$hits
# 
# ## queries
# ### Search in all fields
# Search(index="shakespeare", type="act", q="york")
# 
# ### Searchin specific fields
# Search(index="shakespeare", type="act", q="speaker:KING HENRY IV")$hits$total
# 
# ### Exact phrase search by wrapping in quotes
# Search(index="shakespeare", type="act", q='speaker:"KING HENRY IV"')$hits$total
# 
# ### can specify operators between multiple words parenthetically
# Search(index="shakespeare", type="act", q="speaker:(HENRY OR ARCHBISHOP)")$hits$total
# 
# ### where the field line_number has no value (or is missing)
# Search(index="shakespeare", q="_missing_:line_number")$hits$total
# 
# ### where the field line_number has any non-null value
# Search(index="shakespeare", q="_exists_:line_number")$hits$total
# 
# ### wildcards, either * or ?
# Search(index="shakespeare", q="*ay")$hits$total
# Search(index="shakespeare", q="m?y")$hits$total
# 
# ### regular expressions, wrapped in forward slashes
# Search(index="shakespeare", q="text_entry:/[a-z]/")$hits$total
# 
# ### fuzziness
# Search(index="shakespeare", q="text_entry:ma~")$hits$total
# Search(index="shakespeare", q="text_entry:the~2")$hits$total
# Search(index="shakespeare", q="text_entry:the~1")$hits$total
# 
# ### Proximity searches
# Search(index="shakespeare", q='text_entry:"as hath"~5')$hits$total
# Search(index="shakespeare", q='text_entry:"as hath"~10')$hits$total
# 
# ### Ranges, here where line_id value is between 10 and 20
# Search(index="shakespeare", q="line_id:[10 TO 20]")$hits$total
# 
# ### Grouping
# Search(index="shakespeare", q="(hath OR as) AND the")$hits$total
# 
# # Limit number of hits returned with the size parameter
# Search(index="shakespeare", size=1)
# 
# # Give explanation of search in result
# Search(index="shakespeare", size=1, explain=TRUE)
# 
# ## terminate query after x documents found
# ## setting to 1 gives back one document for each shard
# Search(index="shakespeare", terminate_after=1)
# ## or set to other number
# Search(index="shakespeare", terminate_after=2)
# 
# ## Get version number for each document
# Search(index="shakespeare", version=TRUE, size=2)
# 
# ## Get raw data
# Search(index="shakespeare", type="scene", raw=TRUE)
# 
# ## Curl debugging
# library('httr')
# out <- Search(index="shakespeare", type="line", config=verbose())
# 
# 
# 
# # Query DSL searches - queries sent in the body of the request
# ## Pass in as an R list
# 
# aggs <- list(aggs = list(stats = list(terms = list(field = "text_entry"))))
# Search(index="shakespeare", body=aggs)
# 
# ## or pass in as json query with newlines, easy to read
# aggs <- '{
#     "aggs": {
#         "stats" : {
#             "terms" : {
#                 "field" : "text_entry"
#             }
#         }
#     }
# }'
# Search(index="shakespeare", body=aggs)
# 
# ## or pass in collapsed json string
# aggs <- '{"aggs":{"stats":{"terms":{"field":"text_entry"}}}}'
# Search(index="shakespeare", body=aggs)
# 
# ## Aggregations
# ### Histograms
# aggs <- '{
#     "aggs": {
#         "latbuckets" : {
#            "histogram" : {
#                "field" : "decimalLatitude",
#                "interval" : 5
#            }
#         }
#     }
# }'
# Search(index="gbif", body=aggs, size=0)
# 
# ### Histograms w/ more options
# aggs <- '{
#     "aggs": {
#         "latbuckets" : {
#            "histogram" : {
#                "field" : "decimalLatitude",
#                "interval" : 5,
#                "min_doc_count" : 0,
#                "extended_bounds" : {
#                    "min" : -90,
#                    "max" : 90
#                }
#            }
#         }
#     }
# }'
# Search(index="gbif", body=aggs, size=0)
# 
# ### Ordering the buckets by their doc_count - ascending:
# aggs <- '{
#     "aggs": {
#         "latbuckets" : {
#            "histogram" : {
#                "field" : "decimalLatitude",
#                "interval" : 5,
#                "min_doc_count" : 0,
#                "extended_bounds" : {
#                    "min" : -90,
#                    "max" : 90
#                },
#                "order" : {
#                    "_count" : "desc"
#                }
#            }
#         }
#     }
# }'
# out <- Search(index="gbif", body=aggs, size=0)
# lapply(out$aggregations$latbuckets$buckets, data.frame)
# 
# ### By default, the buckets are returned as an ordered array. It is also possible to
# ### request the response as a hash instead keyed by the buckets keys:
# aggs <- '{
#     "aggs": {
#         "latbuckets" : {
#            "histogram" : {
#                "field" : "decimalLatitude",
#                "interval" : 10,
#                "keyed" : true
#            }
#         }
#     }
# }'
# Search(index="gbif", body=aggs, size=0)
# 
# # match query
# match <- '{"query": {"match" : {"text_entry" : "Two Gentlemen"}}}'
# Search(index="shakespeare", body=match)
# 
# # multi-match (multiple fields that is) query
# mmatch <- '{"query": {"multi_match" : {"query" : "henry", "fields": ["text_entry","play_name"]}}}'
# Search(index="shakespeare", body=mmatch)
# 
# # bool query
# mmatch <- '{
#  "query": {
#    "bool" : {
#      "must_not" : {
#        "range" : {
#          "speech_number" : {
#            "from" : 1, "to": 5
# }}}}}}'
# Search(index="shakespeare", body=mmatch)
# 
# # Boosting query
# boost <- '{
#  "query" : {
#   "boosting" : {
#       "positive" : {
#           "term" : {
#               "play_name" : "henry"
#           }
#       },
#       "negative" : {
#           "term" : {
#               "text_entry" : "thou"
#           }
#       },
#       "negative_boost" : 0.8
#     }
#  }
# }'
# Search(index="shakespeare", body=boost)
# 
# # Fuzzy query
# ## fuzzy query on numerics
# fuzzy <- list(query = list(fuzzy = list(speech_number = 7)))
# Search(index="shakespeare", body=fuzzy)$hits$total
# fuzzy <- list(query = list(fuzzy = list(speech_number = list(value = 7, fuzziness = 4))))
# Search(index="shakespeare", body=fuzzy)$hits$total
# 
# ### fuzzy query on date/time
# fuzzy <- list(query = list(fuzzy = list(eventDate = list(value = "2014-01-29T23:00:00.000",
#    fuzziness = "1d"))))
# out <- Search(index="gbif", body=fuzzy, fields="eventDate")
# out$hits$total
# sapply(out$hits$hits, function(x) x$fields$eventDate) ## sweet!!!
# 
# # geoshape query
# ## not working yets
# geo <- list(query = list(geo_shape = list(location = list(shape = list(type = "envelope",
#    coordinates = "[[2,10],[10,20]]")))))
# geo <- '{
#  "query": {
#    "geo_shape": {
#      "location": {
#        "point": {
#          "type": "envelope",
#          "coordinates": [[2,0],[2.93,100]]
#        }
#      }
#    }
#  }
# }'
# # Search(index="gbifnewgeo", body=geo)
# 
# # range query
# ## with numeric
# body <- list(query=list(range=list(decimalLongitude=list(gte=1, lte=3))))
# Search('gbif', body=body)$hits$total
# 
# body <- list(query=list(range=list(decimalLongitude=list(gte=2.9, lte=10))))
# Search('gbif', body=body)$hits$total
# 
# ## with dates
# body <- list(query=list(range=list(eventDate=list(gte="2012-01-01", lte="now"))))
# Search('gbif', body=body)$hits$total
# 
# body <- list(query=list(range=list(eventDate=list(gte="2014-01-01", lte="now"))))
# Search('gbif', body=body)$hits$total
# 
# # more like this query (more_like_this can be shortened to mlt)
# body <- '{
#  "query": {
#    "more_like_this": {
#      "fields": ["abstract","title"],
#      "like_text": "and then",
#      "min_term_freq": 1,
#      "max_query_terms": 12
#    }
#  }
# }'
# Search('plos', body=body)$hits$total
# 
# body <- '{
#  "query": {
#    "more_like_this": {
#      "fields": ["abstract","title"],
#      "like_text": "cell",
#      "min_term_freq": 1,
#      "max_query_terms": 12
#    }
#  }
# }'
# Search('plos', body=body)$hits$total
# 
# # Highlighting
# body <- '{
#  "query": {
#    "query_string": {
#      "query" : "cell"
#    }
#  },
#  "highlight": {
#    "fields": {
#      "title": {"number_of_fragments": 2}
#    }
#  }
# }'
# out <- Search('plos', 'article', body=body)
# out$hits$total
# sapply(out$hits$hits, function(x) x$`_source`$title[[1]])
# 
# ### Common terms query
# body <- '{
#  "query" : {
#    "common": {
#       "body": {
#            "query": "this is",
#            "cutoff_frequency": 0.01
#        }
#      }
#   }
# }'
# Search('shakespeare', 'line', body=body)
# 
# ## Scrolling search - instead of paging
# Search('shakespeare', q="a*")$hits$total
# res <- Search(index = 'shakespeare', q="a*", scroll="1m")
# res <- Search(index = 'shakespeare', q="a*", scroll="1m", search_type = "scan")
# scroll(scroll_id = res$`_scroll_id`)
# 
# res <- Search(index = 'shakespeare', q="a*", scroll="5m", search_type = "scan")
# out <- list()
# hits <- 1
# while(hits != 0){
#   res <- scroll(scroll_id = res$`_scroll_id`)
#   hits <- length(res$hits$hits)
#   if(hits > 0)
#     out <- c(out, res$hits$hits)
# }
# 
# 
# 
# # Using filters
# ## A bool filter
# body <- '{
#  "query":{
#    "bool": {
#      "must_not" : {
#        "range" : {
#          "year" : { "from" : 2011, "to" : 2012 }
#        }
#      }
#    }
#  }
# }'
# Search('gbif', body = body)$hits$total
# 
# ## Geo filters - fun!
# ### Note that filers have many geospatial filter options, but queries have fewer, and
# ### require a geo_shape mapping
# 
# body <- '{
#  "mappings": {
#    "record": {
#      "properties": {
#          "location" : {"type" : "geo_point"}
#       }
#    }
#  }
# }'
# index_recreate(index='gbifgeopoint', body=body)
# path <- system.file("examples", "gbif_geopoint.json", package = "elastic")
# docs_bulk(path)
# 
# ### Points within a bounding box
# body <- '{
#  "query":{
#    "bool" : {
#      "must" : {
#        "match_all" : {}
#      },
#      "filter":{
#         "geo_bounding_box" : {
#           "location" : {
#             "top_left" : {
#               "lat" : 60,
#               "lon" : 14
#             },
#             "bottom_right" : {
#               "lat" : 40,
#               "lon" : 1
#             }
#           }
#        }
#      }
#    }
#  }
# }'
# out <- Search('gbifgeopoint', body = body)
# out$hits$total
# do.call(rbind, lapply(out$hits$hits, function(x) x$`_source`$location))
# 
# ### Points within distance of a point
# body <- '{
#  "query":{
#    "filtered":{
#      "filter":{
#         "geo_distance" : {
#         "distance" : "200km" ,
#            "location" : {
#               "lon" : 4,
#               "lat" : 50
#             }
#          }
#        }
#      }
#    }
# }'
# out <- Search('gbifgeopoint', body = body)
# out$hits$total
# do.call(rbind, lapply(out$hits$hits, function(x) x$`_source`$location))
# 
# ### Points within distance range of a point
# body <- '{
#  "query":{
#    "bool" : {
#      "must" : {
#        "match_all" : {}
#      },
#      "filter":{
#        "geo_distance_range" : {
#          "from" : "200km",
#          "to" : "400km",
#          "location" : {
#            "lon" : 4,
#            "lat" : 50
#          }
#        }
#      }
#    }
#  }
# }'
# out <- Search('gbifgeopoint', body = body)
# out$hits$total
# do.call(rbind, lapply(out$hits$hits, function(x) x$`_source`$location))
# 
# ### Points within a polygon
# body <- '{
#  "query":{
#    "bool" : {
#      "must" : {
#        "match_all" : {}
#      },
#      "filter":{
#         "geo_polygon" : {
#           "location" : {
#              "points" : [
#                [80.0, -20.0], [-80.0, -20.0], [-80.0, 60.0], [40.0, 60.0], [80.0, -20.0]
#              ]
#            }
#          }
#        }
#      }
#    }
# }'
# out <- Search('gbifgeopoint', body = body)
# out$hits$total
# do.call(rbind, lapply(out$hits$hits, function(x) x$`_source`$location))
# 
# ### Geoshape filters using queries instead of filters
# #### Get data with geojson type location data loaded first
# body <- '{
#  "mappings": {
#    "record": {
#      "properties": {
#          "location" : {"type" : "geo_shape"}
#       }
#    }
#  }
# }'
# index_recreate(index='geoshape', body=body)
# path <- system.file("examples", "gbif_geoshape.json", package = "elastic")
# docs_bulk(path)
# 
# #### Get data with a square envelope, w/ point defining upper left and the other
# #### defining the lower right
# body <- '{
#  "query":{
#    "geo_shape" : {
#      "location" : {
#          "shape" : {
#            "type": "envelope",
#             "coordinates": [[-30, 50],[30, 0]]
#          }
#        }
#      }
#    }
# }'
# out <- Search('geoshape', body = body)
# out$hits$total
# 
# #### Get data with a circle, w/ point defining center, and radius
# body <- '{
#  "query":{
#    "geo_shape" : {
#      "location" : {
#          "shape" : {
#            "type": "circle",
#            "coordinates": [-10, 45],
#            "radius": "2000km"
#          }
#        }
#      }
#    }
# }'
# out <- Search('geoshape', body = body)
# out$hits$total
# 
# #### Use a polygon, w/ point defining center, and radius
# body <- '{
#  "query":{
#    "geo_shape" : {
#      "location" : {
#          "shape" : {
#            "type": "polygon",
#            "coordinates":  [
#               [ [80.0, -20.0], [-80.0, -20.0], [-80.0, 60.0], [40.0, 60.0], [80.0, -20.0] ]
#            ]
#          }
#        }
#      }
#    }
# }'
# out <- Search('geoshape', body = body)
# out$hits$total
# 
# # Missing filter
# body <- '{
#  "query":{
#    "constant_score" : {
#      "filter" : {
#        "missing" : { "field" : "play_name" }
#      }
#    }
#  }
# }'
# Search("shakespeare", body = body)
# 
# # prefix filter
# body <- '{
#  "query": {
#    "bool": {
#      "must": {
#        "prefix" : {
#          "speaker" : "we"
#        }
#      }
#    }
#  }
# }'
# x <- Search("shakespeare", body = body)
# x$hits$total
# vapply(x$hits$hits, "[[", "", c("_source", "speaker"))
# 
# # ids filter
# body <- '{
#  "query":{
#    "bool": {
#      "must": {
#        "ids" : {
#          "values": ["1","2","3","10","2000"]
#        }
#      }
#    }
#  }
# }'
# x <- Search("shakespeare", body = body)
# x$hits$total
# identical(
#  c("1","2","3","10","2000"),
#  vapply(x$hits$hits, "[[", "", "_id")
# )
# 
# # combined prefix and ids filters
# body <- '{
#  "query":{
#    "bool" : {
#      "should" : {
#        "or": [
#        {
#          "ids" : {
#            "values": ["1","2","3","10","2000"]
#          }
#        },
#        {
#          "prefix" : {
#            "speaker" : "we"
#          }
#        }
#      ]
#      }
#    }
#  }
# }'
# x <- Search("shakespeare", body = body)
# x$hits$total
# ## End(Not run)

Run the code above in your browser using DataLab

Get 50% off unlimited learning