Exploring Search Capabilities With Atlas Search

1
public ArrayList<Document> searchMovies(String query) {
2
        List<Document> pipeline = Arrays.asList(new Document("$search",
3
                        new Document("index", "testIndex01")
4
                                .append("text",
5
                                        new Document("query", "cartoon")
6
                                                .append("path", Arrays.asList("title", "plot", "fullplot")))),
7
                        new Document("$project",
8
                        new Document("_id", 0L)
9
                                .append("title", 1L)
10
                                .append("plot", 1L)
11
                                .append("fullplot", 1L)),
12
                        new Document("$limit", 3L));
13
        
14
ArrayList<Document> results = new ArrayList<>();
15
collection.aggregate(pipeline).into(results);
16
return results;
17
    }

1
curl -X GET "http://localhost:8080/search?query=cartoon" | jq

1
[
2
  {
3
    "plot": "Follow Garfield behind the scenes in Cartoon World where he grows bored with his life as a comic strip star.",
4
    "title": "Garfield Gets Real",
5
    "fullplot": "Follow Garfield behind the scenes in Cartoon World where he grows bored with his life as a comic strip star."
6
  },
7
  {
8
    "plot": "A high-profiled documentary about Hergè and his major cartoon success, Tintin, based in part on previously unreleased archive tape footage.",
9
    "title": "Tintin and I",
10
    "fullplot": "A high-profiled documentary about Hergè and his major cartoon success, Tintin, based in part on previously unreleased archive tape footage."
11
  },
12
  {
13
    "plot": "Bugs Bunny reflects on his past cartoon exploits.",
14
    "title": "The Bugs Bunny/Road-Runner Movie",
15
    "fullplot": "The Bugs Bunny/Road Runner Movie is basically a collection of Warner Bros. short cartoon features, \"starring\" the likes of Daffy Duck, Porky Pig and Wile.E.Coyote. These animations are interspersed by Bugs Bunny reminiscing on past events and providing links between the individual animations which are otherwise unconnected. The Road Runner feature at the end consists of sketches from various RR separates (well it does in the 78-minute version anyway)."
16
  }
17
]

1
public ArrayList<Document> searchMoviesWithGenre(String keyword){
2
        List<Document> pipeline = Arrays.asList(new Document("$search",
3
                new Document("index", "testIndex02")
4
                        .append("text",
5
                                new Document("query", keyword)
6
                                        .append("path", "genres"))),
7
                new Document("$project",
8
                new Document("_id", 0L)
9
                        .append("title", 1L)
10
                        .append("genres", 1L)),
11
                new Document("$limit", 5L));
12
ArrayList<Document> results = new ArrayList<>();
13
collection.aggregate(pipeline).into(results);
14
return results;
15
    }

1
curl -X GET "localhost:8080/searchMoviesWithGenre?query=action" | jq

1
[
2
  {
3
    "genres": [
4
      "Action"
5
    ],
6
    "title": "The Perils of Pauline"
7
  },
8
  {
9
    "genres": [
10
      "Action"
11
    ],
12
    "title": "Legacy of Rage"
13
  },
14
  {
15
    "genres": [
16
      "Action"
17
    ],
18
    "title": "Batman Returns"
19
  },
20
  {
21
    "genres": [
22
      "Action"
23
    ],
24
    "title": "Dragon Inn"
25
  },
26
  {
27
    "genres": [
28
      "Action"
29
    ],
30
    "title": "Dikiy vostok"
31
  }
32
]

1
public ArrayList<Document> searchMoviesAndCategorise(){
2
        List<Document> pipeline = Arrays.asList(new Document("$searchMeta",
3
                new Document("index", "testIndex02")
4
                        .append("facet",
5
                new Document("operator",new Document("text",
6
                new Document("query", "movie").append("path", "title")))
7
                        .append("facets",new Document("genresFacet",
8
                new Document("type", "string").append("path", "genres"))
9
                        .append("yearFacet",new Document("type", "number")
10
                        .append("path", "year")
11
                        .append("boundaries", Arrays.asList(1990L, 2000L, 2010L, 2020L)))))));
12
ArrayList<Document> results = new ArrayList<>();
13
collection.aggregate(pipeline).into(results);
14
return results;
15
}

1
curl -X GET "http://localhost:8080/searchMoviesAndCategorise" | jq

1
  {
2
    "count": {
3
      "lowerBound": 125
4
    },
5
    "facet": {
6
      "genresFacet": {
7
        "buckets": [
8
          {
9
            "_id": "Comedy",
10
            "count": 71
11
          },
12
          {
13
            "_id": "Animation",
14
            "count": 42
15
          },
16
          {
17
            "_id": "Adventure",
18
            "count": 40
19
          },
20
          {
21
            "_id": "Family",
22
            "count": 29
23
          },
24
          {
25
            "_id": "Drama",
26
            "count": 19
27
          },
28
          {
29
            "_id": "Action",
30
            "count": 18
31
          },
32
          {
33
            "_id": "Documentary",
34
            "count": 16
35
          },
36
          {
37
            "_id": "Horror",
38
            "count": 9
39
          },
40
          {
41
            "_id": "Fantasy",
42
            "count": 6
43
          },
44
          {
45
            "_id": "Crime",
46
            "count": 5
47
          }
48
        ]
49
      },
50
      "yearFacet": {
51
        "buckets": [
52
          {
53
            "_id": 1990,
54
            "count": 19
55
          },
56
          {
57
            "_id": 2000,
58
            "count": 62
59
          },
60
          {
61
            "_id": 2010,
62
            "count": 27
63
          }
64
        ]
65
      }
66
    }
67
  }
68
]

1
public ArrayList<Document> searchWithIncompleteKeyword(String keyword){
2
      List<Document> pipeline = Arrays.asList(new Document("$search",
3
                      new Document("index", "testIndex03")
4
                              .append("autocomplete",
5
                                      new Document("query", keyword)
6
                                              .append("path", "fullplot"))
7
                              .append("highlight",
8
                                      new Document("path", "fullplot"))),
9
                      new Document("$project",
10
                      new Document("_id", 0L)
11
                              .append("fullplot", 1L)
12
                              .append("highlights",
13
                      new Document("$meta", "searchHighlights"))),
14
                      new Document("$limit", 1L));
15
ArrayList<Document> results = new ArrayList<>();
16
collection.aggregate(pipeline).into(results);
17
return results;
18
    }

1
curl -X GET "http://localhost:8080/searchMoviesWithAutocomplete?query=spa%20cow" | jq

1
[
2
  {
3
    "fullplot": "Julièn Torralba is a former movie stuntman in Almeria, Spain. He and several of his colleagues, who once made a living in American Westerns shot in Spain, now are reduced to doing stunt shows for minuscule audiences on the decaying set built for those old Westerns. Julièn wrestles with dark memories of the death of his son, also a stuntman, and with estrangement from his daughter-in-law Laura and her son Carlos. Carlos, a young boy, becomes intrigued with his late father's life and runs away to join Julièn and his band of has-beens. There Carlos is initiated into the rambunctious life of these hard-drinking faux cowboys. But when Laura, a powerful executive looking for a new site for a tourist resort, learns that Carlos has joined the hated Julièn, she moves to destroy even this remnant of Julièn's once-proud career. Julièn and the cowboys decide to fight back the only way they know how.",
4
    "highlights": [
5
      {
6
        "score": 2.126451015472412,
7
        "path": "fullplot",
8
        "texts": [
9
          {
10
            "value": "Julièn Torralba is a former movie stuntman in Almeria, ",
11
            "type": "text"
12
          },
13
          {
14
            "value": "Spain. He and",
15
            "type": "hit"
16
          }
17
        ]
18
      },
19
      {
20
        "score": 1.518623948097229,
21
        "path": "fullplot",
22
        "texts": [
23
          {
24
            "value": "He and several of his colleagues, who once made a living in American Westerns shot in ",
25
            "type": "text"
26
          },
27
          {
28
            "value": "Spain, now are",
29
            "type": "hit"
30
          },
31
          {
32
            "value": " reduced to doing stunt shows for minuscule audiences on the decaying set built for those old Westerns. ",
33
            "type": "text"
34
          }
35
        ]
36
      },
37
      {
38
        "score": 1.869809865951538,
39
        "path": "fullplot",
40
        "texts": [
41
          {
42
            "value": "There Carlos is initiated into the rambunctious life of these hard-drinking faux ",
43
            "type": "text"
44
          },
45
          {
46
            "value": "cowboys. But when",
47
            "type": "hit"
48
          }
49
        ]
50
      },
51
      {
52
        "score": 1.9461908340454102,
53
        "path": "fullplot",
54
        "texts": [
55
          {
56
            "value": "Julièn and the ",
57
            "type": "text"
58
          },
59
          {
60
            "value": "cowboys decide to",
61
            "type": "hit"
62
          },
63
          {
64
            "value": " fight back the only way they know how.",
65
            "type": "text"
66
          }
67
        ]
68
      }
69
    ]
70
  }
71
]

1
public ArrayList<Document> searchWithMisspelledTitle(String keyword){
2
        List<Document> result = Arrays.asList(new Document("$search",
3
                         new Document("index", "testIndex03")
4
                                .append("text",
5
                         new Document("query", keyword)
6
                                                .append("path", "title")
7
                                                .append("fuzzy",
8
                         new Document("maxEdits", 2L)
9
                                .append("maxExpansions", 100L)))),
10
                         new Document("$project",
11
                         new Document("title", 1L)
12
                                .append("cast", 1L)),
13
                         new Document("$limit", 3L));
14
return collection.aggregate(result).into(new ArrayList<>());
15
    }

1
curl -X GET "localhost:8080/searchMoviesWithIncorrectSpelling?query=Gerti%20the%20Dinosor" | jq

1
[
2
  {
3
    "_id": {
4
      "timestamp": 1463423888,
5
      "date": "2016-05-16T18:38:08.000+00:00"
6
    },
7
    "cast": [
8
      "Winsor McCay",
9
      "George McManus",
10
      "Roy L. McCardell"
11
    ],
12
    "title": "Gertie the Dinosaur"
13
  },
14
  {
15
    "_id": {
16
      "timestamp": 1463423899,
17
      "date": "2016-05-16T18:38:19.000+00:00"
18
    },
19
    "title": "Dinosaur",
20
    "cast": [
21
      "D.B. Sweeney",
22
      "Alfre Woodard",
23
      "Ossie Davis",
24
      "Max Casella"
25
    ]
26
  },
27
  {
28
    "_id": {
29
      "timestamp": 1463423974,
30
      "date": "2016-05-16T18:39:34.000+00:00"
31
    },
32
    "cast": [
33
      "Stan Adelstein",
34
      "Lanice Archer",
35
      "Robert Bakker",
36
      "Philip Currie"
37
    ],
38
    "title": "Dinosaur 13"
39
  }
40
]

1
public ArrayList<Document> searchWithSynonyms(String keyword){
2
        List<Document> result = Arrays.asList(new Document("$search",
3
                        new Document("index", "testIndex04")
4
                                .append("text",
5
                                        new Document("path", "fullplot")
6
                                                .append("query", keyword)
7
                                                .append("synonyms", "synonymName"))),
8
                        new Document("$limit", 10L),
9
                        new Document("$project",
10
                        new Document("_id", 0L)
11
                                .append("title", 1L)
12
                                .append("fullplot", 1L)
13
                                .append("score",
14
                                        new Document("$meta", "searchScore"))),
15
                       new Document("$limit", 3L));
16
        return collection.aggregate(result).into(new ArrayList<>());
17
    }

1
[
2
  {
3
    mappingType: 'explicit',
4
    input: [ 'love', 'romance' ],
5
    synonyms: [ 'love', 'romance' ]
6
  },
7
  {
8
    mappingType: 'equivalent',
9
    synonyms: [ 'car', 'vehicle', 'automobile' ]
10
  }
11
]

1
curl -X GET "localhost:8080/searchMoviesWithSynonyms?query=love" | jq

1
[
2
  {
3
    "title": "Oh, Woe Is Me",
4
    "fullplot": "Romance about Simon Donnadieu and his decision to leave his ever-loving wife Rachel.",
5
    "score": 3.9741177558898926
6
  },
7
  {
8
    "title": "27 Missing Kisses",
9
    "fullplot": "The summerly adventures of teen Sybilla, who falls in love with a middle-aged father, while being romanced by the his teen son.",
10
    "score": 3.8209657669067383
11
  },
12
  {
13
    "title": "The End of the Affair",
14
    "fullplot": "In wartorn London Maurice Bendrix falls in love with neighbor Sarah Miles. They begin an illicit romance behind Sarah's husband's back. While war does not last forever, neither does love in this existentialist tale.",
15
    "score": 3.753319263458252
16
  }
17
]

1
public void deleteSearchIndexes(String dbName, String collectionName) {
2
        MongoDatabase database = mongoClient.getDatabase(dbName);
3
        MongoCollection<Document> collection = database.getCollection(collectionName);
4
5
        List<String> indexNames = new ArrayList<>();
6
        for (Document indexInfo : collection.listSearchIndexes()) {
7
            String indexName = indexInfo.getString("name");
8
            if (!"_id_".equals(indexName)) {
9
                indexNames.add(indexName);
10
            }
11
        }
12
        // Drop each index using its name from the array
13
        for (String indexName : indexNames) {
14
            collection.dropSearchIndex(indexName);
15
        }
16
        System.out.println("Deleted all indexes created");
17
    }

1
curl -X DELETE "localhost:8080/deleteSearchIndexes?dbName=<dbName>&collectionName=<collectionName>"