Please use the form below to provide your feedback. Because your feedback is valuable to us, the information you submit in this form is recorded in our issue tracking system (JIRA), which is publicly available. You can track the status of your feedback using the ticket number displayed in the dialog once you submit the form.

QueryBuilder

      +

      Description — How to use QueryBuilder to build effective queries with Couchbase Lite on Android
      Related Content — Predictive Queries | Live Queries | Indexing

      The examples used here are based on the Travel Sample app and data introduced in the Couchbase Mobile Workshop tutorial

      Introduction

      Couchbase Lite for Android provides two ways to build and run database queries; the QueryBuilder API described in this topic and SQL++ for Mobile.

      Database queries defined with the QueryBuilder API use the query statement format shown in Example 1. The structure and semantics of the query format are based on Couchbase’s SQL++ query language.

      Example 1. Query Format
      SELECT ____
FROM 'data-source'
WHERE ____,
JOIN ____
GROUP BY ____
ORDER BY ____
      Query Components
      Component Description

      SELECT statement

      The document properties that will be returned in the result set

      FROM

      The data source to query the documents from - the collection of the database.

      WHERE statement

      The query criteria
      The `SELECT`ed properties of documents matching this criteria will be returned in the result set

      JOIN statement

      The criteria for joining multiple documents

      GROUP BY statement

      The criteria used to group returned items in the result set

      ORDER BY statement

      The criteria used to order the items in the result set
      We recommend working through the query section of the Couchbase Mobile Workshop tutorial as a good way to build your skills in this area.

      SELECT statement

      In this section

      Return Selected Properties  |   Return All Properties

      Related

      Handling result sets

      Use the SELECT statement to specify which properties you want to return from the queried documents. You can opt to retrieve entire documents, or just the specific properties you need.

      Return All Properties

      Use the SelectResult.all() method to return all the properties of selected documents — see: Example 2.

      Example 2. Using SELECT to Retrieve All Properties

      This query shows how to retrieve all properties from all documents in your database.

      • Kotlin

      • Java

      val queryAll = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
      Query query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")));

      The query.execute statement returns the results in a dictionary, where the key is the database name — see Example 3.

      Example 3. ResultSet Format from SelectResult.all()
      [
  {
    "travel-sample": { (1)
      "callsign": "MILE-AIR",
      "country": "United States",
      "iata": "Q5",
      "icao": "MLA",
      "id": 10,
      "name": "40-Mile Air",
      "type": "airline"
    }
  },
  {
    "travel-sample": { (2)
      "callsign": "ALASKAN-AIR",
      "country": "United States",
      "iata": "AA",
      "icao": "AAA",
      "id": 10,
      "name": "Alaskan Airways",
      "type": "airline"
    }
  }
]
      1 The result for the first document matching the query criteria.
      2 The result for the next document matching the query criteria.

      See: Result Sets for more on processing query results.

      Return Selected Properties

      To access only specific properties, specify a comma-separated list of SelectResult expressions, one for each property, in the select statement of your query  — see: Example 4

      Example 4. Using SELECT to Retrieve Specific Properties

      In this query we retrieve and then print the _id, type and name properties of each document.

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"),
        SelectResult.property("type")
    )
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .orderBy(Ordering.expression(Meta.id))

query.execute().use { rs ->
    rs.forEach {
        log("hotel id ->${it.getString("id")}")
        log("hotel name -> ${it.getString("name")}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"),
        SelectResult.property("type"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .orderBy(Ordering.expression(Meta.id));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log("hotel id -> " + result.getString("id"));
        Logger.log("hotel name -> " + result.getString("name"));
    }
}

      The query.execute statement returns one or more key-value pairs, one for each SelectResult expression, with the property-name as the key — see Example 5

      Example 5. Select Result Format
      [
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]
      1 The result for the first document matching the query criteria.
      2 The result for the next document matching the query criteria.

      See: Result Sets for more on processing query results.

      WHERE statement

      In this section

      Comparison Operators  |   Collection Operators  |   Like Operator  |   Regex Operator  |   Deleted Document

      Like SQL, you can use the WHERE statement to choose which documents are returned by your query. The select statement takes in an Expression. You can chain any number of Expressions in order to implement sophisticated filtering capabilities.

      Comparison Operators

      The Expression Comparators can be used in the WHERE statement to specify on which property to match documents. In the example below, we use the equalTo operator to query documents where the type property equals "hotel".

      [
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]
      Example 6. Using Where

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .limit(Expression.intValue(10))

query.execute().use { rs ->
    rs.forEach { result ->
        result.getDictionary("myDatabase")?.let {
            log("name -> ${it.getString("name")}")
            log("type -> ${it.getString("type")}")
        }
    }
}
      Query query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .limit(Expression.intValue(10));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Dictionary all = result.getDictionary(collectionName);
        Logger.log("name -> " + all.getString("name"));
        Logger.log("type -> " + all.getString("type"));
    }
}

      Collection Operators

      ArrayFunction Collection Operators are useful to check if a given value is present in an array.

      CONTAINS Operator

      The following example uses the ArrayFunction to find documents where the public_likes array property contains a value equal to "Armani Langworth".

      {
    "_id": "hotel123",
    "name": "Apple Droid",
    "public_likes": ["Armani Langworth", "Elfrieda Gutkowski", "Maureen Ruecker"]
}

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"),
        SelectResult.property("public_likes")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("hotel"))
            .and(
                ArrayFunction.contains(
                    Expression.property("public_likes"),
                    Expression.string("Armani Langworth")
                )
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("public_likes -> ${it.getArray("public_likes")?.toList()}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"),
        SelectResult.property("public_likes"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel"))
        .and(ArrayFunction
            .contains(Expression.property("public_likes"), Expression.string("Armani Langworth"))));
try (ResultSet results = query.execute()) {
    for (Result result: results) {
        Logger.log("public_likes -> " + result.getArray("public_likes").toList());
    }
}

      IN Operator

      The IN operator is useful when you need to explicitly list out the values to test against. The following example looks for documents whose first, last or username property value equals "Armani".

      • Kotlin

      • Java

      val query = QueryBuilder.select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(
        Expression.string("Armani").`in`(
            Expression.property("first"),
            Expression.property("last"),
            Expression.property("username")
        )
    )

query.execute().use { rs ->
    rs.forEach {
        log("public_likes -> ${it.toMap()}")
    }
}
      Expression[] values = new Expression[] {
    Expression.property("first"),
    Expression.property("last"),
    Expression.property("username")
};

Query query = QueryBuilder.select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.string("Armani").in(values));

      Like Operator

      In this section

      String Matching  |   Wildcard Match  |   Wildcard Character Match

      String Matching

      The Like() operator can be used for string matching — see Example 7

      The like operator performs case sensitive matches.
      To perform case insensitive matching, use Function.lower or Function.upper to ensure all comparators have the same case, thereby removing the case issue.

      This query returns landmark type documents where the name matches the string "Royal Engineers Museum", regardless of how it is capitalized (so, it selects "royal engineers museum", "ROYAL ENGINEERS MUSEUM" and so on).

      Example 7. Like with case-insensitive matching

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("landmark"))
            .and(
                Function.lower(Expression.property("name"))
                    .like(Expression.string("royal engineers museum"))
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("name -> ${it.getString("name")}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
        .and(Function.lower(Expression.property("name")).like(Expression.string("royal engineers museum"))));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log("name -> " + result.getString("name"));
    }
}

      Note the use of Function.lower to transform name values to the same case as the literal comparator.

      Wildcard Match

      We can use % sign within a like expression to do a wildcard match against zero or more characters. Using wildcards allows you to have some fuzziness in your search string.

      In Example 8 below, we are looking for documents of type "landmark" where the name property matches any string that begins with "eng" followed by zero or more characters, the letter "e", followed by zero or more characters. Once again, we are using Function.lower to make the search case insensitive.

      So "landmark" documents with names such as "Engineers", "engine", "english egg" and "England Eagle". Notice that the matches may span word boundaries.

      Example 8. Wildcard Matches

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("landmark"))
            .and(
                Function.lower(Expression.property("name"))
                    .like(Expression.string("eng%e%"))
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("name -> ${it.getString("name")}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
        .and(Function.lower(Expression.property("name")).like(Expression.string("eng%e%"))));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log("name ->  " + result.getString("name"));
    }
}

      Wildcard Character Match

      We can use an _ sign within a like expression to do a wildcard match against a single character.

      In Example 9 below, we are looking for documents of type "landmark" where the name property matches any string that begins with "eng" followed by exactly 4 wildcard characters and ending in the letter "r". The query returns "landmark" type documents with names such as "Engineer", "engineer" and so on.

      Example 9. Wildcard Character Matching

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("landmark"))
            .and(
                Function.lower(Expression.property("name"))
                    .like(Expression.string("eng____r"))
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("name -> ${it.getString("name")}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
        .and(Function.lower(Expression.property("name")).like(Expression.string("eng____r"))));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log("name -> " + result.getString("name"));
    }
}

      Regex Operator

      Similar to the wildcards in like expressions, regex based pattern matching allow you to introduce an element of fuzziness in your search string — see the code shown in Example 10.

      The regex operator is case sensitive, use upper or lower functions to mitigate this if required.
      Example 10. Using Regular Expressions

      This example returns documents with a `type` of "landmark" and a `name` property that matches any string that begins with "eng" and ends in the letter "e".

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("landmark"))
            .and(
                Function.lower(Expression.property("name"))
                    .regex(Expression.string("\\beng.*r\\b"))
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("name -> ${it.getString("name")}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
        .and(Function.lower(Expression.property("name")).regex(Expression.string("\\beng.*r\\b"))));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log("name -> " + result.getString("name"));
    }
}
      1 The \b specifies that the match must occur on word boundaries.
      For more on the regex spec used by Couchbase Lite see cplusplus regex reference page

      Deleted Document

      You can query documents that have been deleted (tombstones) [1] as shown in Example 11.

      Example 11. Query to select Deleted Documents

      This example shows how to query deleted documents in the database. It returns is an array of key-value pairs.

      • Kotlin

      • Java

      // Query documents that have been deleted
val query = QueryBuilder
    .select(SelectResult.expression(Meta.id))
    .from(DataSource.collection(collection))
    .where(Meta.deleted)
      // Query documents that have been deleted
Query query = QueryBuilder
    .select(SelectResult.expression(Meta.id))
    .from(DataSource.collection(collection))
    .where(Meta.deleted);

      JOIN statement

      The JOIN clause enables you to select data from multiple documents that have been linked by criteria specified in the JOIN statement. For example to combine airline details with route details, linked by the airline id — see Example 12.

      Example 12. Using JOIN to Combine Document Details

      This example JOINS the document of type route with documents of type airline using the document ID (id) on the _airline document and airlineid on the route document.

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Expression.property("name").from("airline")),
        SelectResult.expression(Expression.property("callsign").from("airline")),
        SelectResult.expression(Expression.property("destinationairport").from("route")),
        SelectResult.expression(Expression.property("stops").from("route")),
        SelectResult.expression(Expression.property("airline").from("route"))
    )
    .from(DataSource.collection(collection).`as`("airline"))
    .join(
        Join.join(DataSource.collection(collection).`as`("route"))
            .on(
                Meta.id.from("airline")
                    .equalTo(Expression.property("airlineid").from("route"))
            )
    )
    .where(
        Expression.property("type").from("route").equalTo(Expression.string("route"))
            .and(
                Expression.property("type").from("airline")
                    .equalTo(Expression.string("airline"))
            )
            .and(
                Expression.property("sourceairport").from("route")
                    .equalTo(Expression.string("RIX"))
            )
    )
query.execute().use { rs ->
    rs.forEach {
        log("name -> ${it.toMap()}")
    }
}
      Query query = QueryBuilder.select(
        SelectResult.expression(Expression.property("name").from("airline")),
        SelectResult.expression(Expression.property("callsign").from("airline")),
        SelectResult.expression(Expression.property("destinationairport").from("route")),
        SelectResult.expression(Expression.property("stops").from("route")),
        SelectResult.expression(Expression.property("airline").from("route")))
    .from(DataSource.collection(collection).as("airline"))
    .join(Join.join(DataSource.collection(collection).as("route"))
        .on(Meta.id.from("airline").equalTo(Expression.property("airlineid").from("route"))))
    .where(Expression.property("type").from("route").equalTo(Expression.string("route"))
        .and(Expression.property("type").from("airline").equalTo(Expression.string("airline")))
        .and(Expression.property("sourceairport").from("route").equalTo(Expression.string("RIX"))));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log(result.toMap().toString());
    }
}

      GROUP BY statement

      You can perform further processing on the data in your result set before the final projection is generated.

      The following example looks for the number of airports at an altitude of 300 ft or higher and groups the results by country and timezone.

      Data Model for Example
      {
    "_id": "airport123",
    "type": "airport",
    "country": "United States",
    "geo": { "alt": 456 },
    "tz": "America/Anchorage"
}
      Example 13. Query using GroupBy

      This example shows a query that selects all airports with an altitude above 300ft. The output (a count, $1) is grouped by country, within timezone.

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Function.count(Expression.string("*"))),
        SelectResult.property("country"),
        SelectResult.property("tz")
    )
    .from(DataSource.collection(collection))
    .where(
        Expression.property("type").equalTo(Expression.string("airport"))
            .and(Expression.property("geo.alt").greaterThanOrEqualTo(Expression.intValue(300)))
    )
    .groupBy(
        Expression.property("country"), Expression.property("tz")
    )
    .orderBy(Ordering.expression(Function.count(Expression.string("*"))).descending())
query.execute().use { rs ->
    rs.forEach {
        log(
            "There are ${it.getInt("$1")} airports on the ${
                it.getString("tz")
            } timezone located in ${
                it.getString("country")
            } and above 300ft"
        )
    }
}
      Query query = QueryBuilder.select(
        SelectResult.expression(Function.count(Expression.string("*"))),
        SelectResult.property("country"),
        SelectResult.property("tz"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("airport"))
        .and(Expression.property("geo.alt").greaterThanOrEqualTo(Expression.intValue(300))))
    .groupBy(
        Expression.property("country"),
        Expression.property("tz"))
    .orderBy(Ordering.expression(Function.count(Expression.string("*"))).descending());

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log(String.format(
            Locale.getDefault(),
            "There are %d airports on the %s timezone located in %s and above 300ft",
            result.getInt("$1"),
            result.getString("tz"),
            result.getString("country")));
    }
}

      The query shown in Example 13 generates the following output:

      There are 138 airports on the Europe/Paris timezone located in France and above 300 ft
      There are 29 airports on the Europe/London timezone located in United Kingdom and above 300 ft
      There are 50 airports on the America/Anchorage timezone located in United States and above 300 ft
      There are 279 airports on the America/Chicago timezone located in United States and above 300 ft
      There are 123 airports on the America/Denver timezone located in United States and above 300 ft

      ORDER BY statement

      It is possible to sort the results of a query based on a given expression result — see Example 14

      Example 14. Query using OrderBy

      This example shows a query that returns documents of type equal to "hotel" sorted in ascending order by the value of the title property.

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .orderBy(Ordering.property("name").ascending())
    .limit(Expression.intValue(10))

query.execute().use { rs ->
    rs.forEach {
        log("${it.toMap()}")
    }
}
      Query query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"))
    .from(DataSource.collection(collection))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .orderBy(Ordering.property("name").ascending())
    .limit(Expression.intValue(10));

try (ResultSet resultSet = query.execute()) {
    for (Result result: resultSet) {
        Logger.log(result.toMap().toString());
    }
}

      The query shown in Example 14 generates the following output:

      Aberdyfi
Achiltibuie
Altrincham
Ambleside
Annan
Ardèche
Armagh
Avignon

      Date/Time Functions

      Couchbase Lite documents support a date type that internally stores dates in ISO 8601 with the GMT/UTC timezone.

      Couchbase Lite’s Query Builder API [1] includes four functions for date comparisons.

      Function.StringToMillis(Expression.Property("date_time"))

      The input to this will be a validly formatted ISO 8601 date_time string. The end result will be an expression (with a numeric content) that can be further input into the query builder.

      Function.StringToUTC(Expression.Property("date_time"))

      The input to this will be a validly formatted ISO 8601 date_time string. The end result will be an expression (with string content) that can be further input into the query builder.

      Function.MillisToString(Expression.Property("date_time"))

      The input for this is a numeric value representing milliseconds since the Unix epoch. The end result will be an expression (with string content representing the date and time as an ISO 8601 string in the device’s timezone) that can be further input into the query builder.

      Function.MillisToUTC(Expression.Property("date_time"))

      The input for this is a numeric value representing milliseconds since the Unix epoch. The end result will be an expression (with string content representing the date and time as a UTC ISO 8601 string) that can be further input into the query builder.

      Result Sets

      In this section

      Processing  |   Select All Properties  |   Select Specific Properties  |   Select Document Id Only  |   Select Count-only  |   Handling Pagination

      Processing

      This section shows how to handle the returned result sets for different types of SELECT statements.

      The result set format and its handling varies slightly depending on the type of SelectResult statements used. The result set formats you may encounter include those generated by :

      To process the results of a query, you first need to execute it using Query.execute.

      The execution of a Couchbase Lite for Android’s database query typically returns an array of results, a result set.

      • The result set of an aggregate, count-only, query is a key-value pair — see Select Count-only — which you can access using the count name as its key.

      • The result set of a query returning document properties is an array.
        Each array row represents the data from a document that matched your search criteria (the WHERE statements) The composition of each row is determined by the combination of SelectResult expressions provided in the SELECT statement. To unpack these result sets you need to iterate this array.

      Select All Properties

      Query

      The Select statement for this type of query, returns all document properties for each document matching the query criteria — see Example 15

      Example 15. Query selecting All Properties

      • Kotlin

      • Java

      val listQuery = QueryBuilder.select(SelectResult.all())
    .from(DataSource.collection(collection))
      Query listQuery = QueryBuilder.select(SelectResult.all())
    .from(DataSource.collection(collection));

      Result Set Format

      The result set returned by queries using SelectResult.all is an array of dictionary objects — one for each document matching the query criteria.

      For each result object, the key is the database name and the 'value' is a dictionary representing each document property as a key-value pair — see: Example 16.

      Example 16. Format of Result Set (All Properties)
      [
  {
    "travel-sample": { (1)
      "callsign": "MILE-AIR",
      "country": "United States",
      "iata": "Q5",
      "icao": "MLA",
      "id": 10,
      "name": "40-Mile Air",
      "type": "airline"
    }
  },
  {
    "travel-sample": { (2)
      "callsign": "ALASKAN-AIR",
      "country": "United States",
      "iata": "AA",
      "icao": "AAA",
      "id": 10,
      "name": "Alaskan Airways",
      "type": "airline"
    }
  }
]
      1 The result for the first document matching the query criteria.
      2 The result for the next document matching the query criteria.

      Result Set Access

      In this case access the retrieved document properties by converting each row’s value, in turn, to a dictionary — as shown in Example 17.

      Example 17. Using Document Properties (All)

      • Kotlin

      • Java

      val hotels = mutableMapOf<String, Hotel>()
listQuery.execute().use { rs ->
    rs.allResults().forEach {
        // get the k-v pairs from the 'hotel' key's value into a dictionary
        val thisDocsProps = it.getDictionary(0) (1)
        val thisDocsId = thisDocsProps!!.getString("id")
        val thisDocsName = thisDocsProps.getString("name")
        val thisDocsType = thisDocsProps.getString("type")
        val thisDocsCity = thisDocsProps.getString("city")

        // Alternatively, access results value dictionary directly
        val id = it.getDictionary(0)?.getString("id").toString() (2)
        hotels[id] = Hotel(
            id,
            it.getDictionary(0)?.getString("type"),
            it.getDictionary(0)?.getString("name"),
            it.getDictionary(0)?.getString("city"),
            it.getDictionary(0)?.getString("country"),
            it.getDictionary(0)?.getString("description")
        )
    }
}
      Map<String, Hotel> hotels = new HashMap<>();
try (ResultSet resultSet = listQuery.execute()) {
    for (Result result: resultSet) {
        // get the k-v pairs from the 'hotel' key's value into a dictionary
        Dictionary docsProp = result.getDictionary(0); (1)
        String docsId = docsProp.getString("id");
        String docsName = docsProp.getString("Name");
        String docsType = docsProp.getString("Type");
        String docsCity = docsProp.getString("City");

        // Alternatively, access results value dictionary directly
        final Hotel hotel = new Hotel();
        hotel.setId(result.getDictionary(0).getString("id")); (2)
        hotel.setType(result.getDictionary(0).getString("Type"));
        hotel.setName(result.getDictionary(0).getString("Name"));
        hotel.setCity(result.getDictionary(0).getString("City"));
        hotel.setCountry(result.getDictionary(0).getString("Country"));
        hotel.setDescription(result.getDictionary(0).getString("Description"));
        hotels.put(hotel.getId(), hotel);
    }
}
      1 The dictionary of document properties using the database name as the key. You can add this dictionary to an array of returned matches, for processing elsewhere in the app.
      2 Alternatively you can access the document properties here, by using the property names as keys to the dictionary object.

      Select Specific Properties

      Query

      Here we use SelectResult.expression(property("<property-name>"))) to specify the document properties we want our query to return — see: Example 18.

      Example 18. Query selecting Specific Properties

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.collection(collection))
      
Query listQuery =
    QueryBuilder.select(
            SelectResult.expression(Meta.id),
            SelectResult.property("name"),
            SelectResult.property("Name"),
            SelectResult.property("Type"),
            SelectResult.property("City"))
        .from(DataSource.collection(collection));

      Result Set Format

      The result set returned when selecting only specific document properties is an array of dictionary objects — one for each document matching the query criteria.

      Each result object comprises a key-value pair for each selected document property — see Example 19

      Example 19. Format of Result Set (Specific Properties)
      [
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]
      1 The result for the first document matching the query criteria.
      2 The result for the next document matching the query criteria.

      Result Set Access

      Access the retrieved properties by converting each row into a dictionary — as shown in Example 20.

      Example 20. Using Returned Document Properties (Specific Properties)

      • Kotlin

      • Java

      query.execute().use { rs ->
    rs.allResults().forEach {
        log("Hotel name -> ${it.getString("name")}, in ${it.getString("country")}")
    }
}
      HashMap<String, Hotel> hotels = new HashMap<>();
try (ResultSet resultSet = listQuery.execute()) {
    for (Result result: resultSet) {

        // get data direct from result k-v pairs
        final Hotel hotel = new Hotel();
        hotel.setId(result.getString("id"));
        hotel.setType(result.getString("Type"));
        hotel.setName(result.getString("Name"));
        hotel.setCity(result.getString("City"));

        // Store created hotel object in a hashmap of hotels
        hotels.put(hotel.getId(), hotel);

        // Get result k-v pairs into a 'dictionary' object
        Map<String, Object> thisDocsProps = result.toMap();
        String docId =
            thisDocsProps.getOrDefault("id", null).toString();
        String docName =
            thisDocsProps.getOrDefault("Name", null).toString();
        String docType =
            thisDocsProps.getOrDefault("Type", null).toString();
        String docCity =
            thisDocsProps.getOrDefault("City", null).toString();
    }
}

      Select Document Id Only

      Query

      You would typically use this type of query if retrieval of document properties directly would consume excessive amounts of memory and-or processing time — see: Example 21.

      Example 21. Query selecting only Doc Id

      • Kotlin

      • Java

      val query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id).`as`("hotelId")
    )
    .from(DataSource.collection(collection))
      Query listQuery =
    QueryBuilder.select(SelectResult.expression(Meta.id).as("metaID"))
        .from(DataSource.collection(collection));

      Result Set Format

      The result set returned by queries using a SelectResult expression of the form SelectResult.expression(meta.id) is an array of dictionary objects — one for each document matching the query criteria. Each result object has id as the key and the ID value as its value — -see Example 22.

      Example 22. Format of Result Set (Doc Id only)
      [
  {
    "id": "hotel123"
  },
  {
    "id": "hotel456"
  },
]

      Result Set Access

      In this case, access the required document’s properties by unpacking the id and using it to get the document from the database — see: Example 23.

      Example 23. Using Returned Document Properties (Document Id)

      • Kotlin

      • Java

      query.execute().use { rs ->
    rs.allResults().forEach {
        log("hotel id ->${it.getString("hotelId")}")
    }
}
      try (ResultSet rs = listQuery.execute()) {
    for (Result result: rs.allResults()) {

        // get the ID form the result's k-v pair array
        String thisDocsId = result.getString("metaID"); (1)

        // Get document from DB using retrieved ID
        Document thisDoc = collection.getDocument(thisDocsId);

        // Process document as required
        String thisDocsName = thisDoc.getString("Name");
    }
}
      1 Extract the Id value from the dictionary and use it to get the document from the database

      Select Count-only

      Query

      Example 24. Query selecting a Count-only

      • Kotlin

      • Java

      
val query = QueryBuilder
    .select(
        SelectResult.expression(Function.count(Expression.string("*"))).`as`("mycount")
    ) (1)
    .from(DataSource.collection(collection))
      Query listQuery = QueryBuilder.select(
        SelectResult.expression(Function.count(Expression.string("*"))).as("mycount")) (1)
    .from(DataSource.collection(collection));
      1 The alias name, mycount, is used to access the count value.

      Result Set Format

      The result set returned by a count such as Select.expression(Function.count(Expression.all))) is a key-value pair. The key is the count name, as defined using SelectResult.as — see: Example 25 for the format and Example 24 for the query.

      Example 25. Format of Result Set (Count)
      {
  "mycount": 6
}
      1 The key-value pair returned by a count.

      Result Set Access

      Access the count using its alias name (mycount in this example) — see Example 26

      Example 26. Using Returned Document Properties (Count)

      • Kotlin

      • Java

      query.execute().use { rs ->
    rs.allResults().forEach {
        log("name -> ${it.getInt("mycount")}")
    }
}
      try (ResultSet resultSet = listQuery.execute()) {
    for (Result result: resultSet) {

        // Retrieve count using key 'mycount'
        Integer altDocId = result.getInt("mycount");

        // Alternatively, use the index
        Integer orDocId = result.getInt(0);
    }
}

// Or even leave out the for-loop altogether
int resultCount;
try (ResultSet resultSet = listQuery.execute()) {
    resultCount = resultSet.next().getInt("mycount");
}
      1 Get the count using the SelectResult.as alias, which is used as its key.

      Handling Pagination

      One way to handle pagination in high-volume queries is to retrieve the results in batches. Use the limit and offset feature, to return a defined number of results starting from a given offset — see: Example 27.

      Example 27. Query Pagination

      • Kotlin

      • Java

      val thisOffset = 0
val thisLimit = 20
val listQuery = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .limit(
        Expression.intValue(thisLimit),
        Expression.intValue(thisOffset)
    ) (1)
      
int thisOffset = 0;
int thisLimit = 20;

Query listQuery =
    QueryBuilder
        .select(SelectResult.all())
        .from(DataSource.collection(collection))
        .limit(
            Expression.intValue(thisLimit),
            Expression.intValue(thisOffset)); (1)
      1 Return a maximum of limit results starting from result number offset
      For more on using the QueryBuilder API, see our blog: Introducing the Query Interface in Couchbase Mobile

      JSON Result Sets

      Couchbase Lite for Android provides a convenience API to convert query results to JSON strings.

      Example 28. Using JSON Results

      Use Result.toJSON() to transform your result string into a JSON string, which can easily be serialized or used as required in your application. See <> for a working example.

      • Kotlin

      • Java

      // Uses Jackson JSON processor
val mapper = ObjectMapper()
val hotels = mutableListOf<Hotel>()

listQuery.execute().use { rs ->
    rs.forEach {

        // Get result as JSON string
        val json = it.toJSON() (1)

        // Get Hashmap from JSON string
        val dictFromJSONstring = mapper.readValue(json, HashMap::class.java) (2)

        // Use created hashmap
        val hotelId = dictFromJSONstring["id"].toString() //
        val hotelType = dictFromJSONstring["type"].toString()
        val hotelname = dictFromJSONstring["name"].toString()

        // Get custom object from JSON string
        val thisHotel = mapper.readValue(json, Hotel::class.java) (3)
        hotels.add(thisHotel)
    }
}
      // Uses Jackson JSON processor
ObjectMapper mapper = new ObjectMapper();
List<Hotel> hotels = new ArrayList<>();

try (ResultSet rs = listQuery.execute()) {
    for (Result result: rs) {
        String json = result.toJSON();
        Map<String, String> dictFromJSONstring = mapper.readValue(json, HashMap.class);

        String hotelId = dictFromJSONstring.get("id");
        String hotelType = dictFromJSONstring.get("type");
        String hotelname = dictFromJSONstring.get("name");

        // Get custom object from JSON string
        Hotel thisHotel = mapper.readValue(json, Hotel.class);
        hotels.add(thisHotel);
    }
}
      JSON String Format

      If your query selects ALL then the JSON format will be:

      {
  database-name: {
    key1: "value1",
    keyx: "valuex"
  }
}

      If your query selects a sub-set of available properties then the JSON format will be:

      {
  key1: "value1",
  keyx: "valuex"
}

      Predictive Query

      Enterprise Edition only
      Predictive Query is an Enterprise Edition feature.

      Predictive Query enables Couchbase Lite queries to use machine learning, by providing query functions that can process document data (properties or blobs) via trained ML models.

      Let’s consider an image classifier model that takes a picture as input and outputs a label and probability.

      predictive diagram

      To run a predictive query with a model as the one shown above, you must implement the following steps.

      1. Integrate the Model

      2. Register the Model

      3. Create an Index (Optional)

      4. Run a Prediction Query

      5. Deregister the Model

      Integrate the Model

      To integrate a model with Couchbase Lite, you must implement the PredictiveModel interface which has only one function called predict() — see: Example 29.

      Example 29. Integrating a predictive model

      • Kotlin

      • Java

      // tensorFlowModel is a fake implementation
object TensorFlowModel {
    fun predictImage(data: ByteArray?): Map<String, Any?> = TODO()
}

object ImageClassifierModel : PredictiveModel {
    const val NAME = "ImageClassifier"

    // this would be the implementation of the ml model you have chosen
    override fun predict(input: Dictionary) = input.getBlob("photo")?.let {
        MutableDictionary(TensorFlowModel.predictImage(it.content)) (1)
    }
}
      class ImageClassifierModel implements PredictiveModel {
    @Override
    public Dictionary predict(@NonNull Dictionary input) {
        Blob blob = input.getBlob("photo");
        if (blob == null) { return null; }

        // tensorFlowModel is a fake implementation
        // this would be the implementation of the ml model you have chosen
        return new MutableDictionary(TensorFlowModel.predictImage(blob.getContent())); (1)
    }
}

@SuppressWarnings("unused")
class LogTestLogger implements com.couchbase.lite.Logger {
    @NonNull
    private final LogLevel level;

    public LogTestLogger(@NonNull LogLevel level) { this.level = level; }

    @NonNull
    @Override
    public LogLevel getLevel() { return level; }

    @Override
    public void log(@NonNull LogLevel level, @NonNull LogDomain domain, @NonNull String message) {

    }
}


@SuppressWarnings("unused")
class TensorFlowModel {
    public static Map<String, Object> predictImage(byte[] data) {
        return null;
    }
}
    // tensorFlowModel is a fake implementation
    // this would be the implementation of the ml model you have chosen
    public static class TensorFlowModel {
        public static Map<String, Object> predictImage(byte[] data) {
            return null;
        }
    }

    public static class ImageClassifierModel implements PredictiveModel {
        @Override
        public Dictionary predict(@NonNull Dictionary input) {
            Blob blob = input.getBlob("photo");

            // tensorFlowModel is a fake implementation
            // this would be the implementation of the ml model you have chosen
            return (blob == null)
                ? null
                : new MutableDictionary(TensorFlowModel.predictImage(blob.getContent())); (1)
        }
    }
      1 The predict(input) -> output method provides the input and expects the result of using the machine learning model. The input and output of the predictive model is a DictionaryObject. Therefore, the supported data type will be constrained by the data type that the DictionaryObject supports.

      Register the Model

      To register the model you must create a new instance and pass it to the Database.prediction.registerModel static method.

      Example 30. Registering a predictive model

      • Kotlin

      • Java

      Database.prediction.registerModel("ImageClassifier", ImageClassifierModel)
      Database.prediction.registerModel("ImageClassifier", new ImageClassifierModel());

      Create an Index

      Creating an index for a predictive query is highly recommended. By computing the predictions during writes and building a prediction index, you can significantly improve the speed of prediction queries (which would otherwise have to be computed during reads).

      There are two types of indexes for predictive queries:

      Value Index

      The code below creates a value index from the "label" value of the prediction result. When documents are added or updated, the index will call the prediction function to update the label value in the index.

      Example 31. Creating a value index

      • Kotlin

      • Java

      collection.createIndex(
    "value-index-image-classifier",
    IndexBuilder.valueIndex(ValueIndexItem.expression(Expression.property("label")))
)
      collection.createIndex(
    "value-index-image-classifier",
    IndexBuilder.valueIndex(ValueIndexItem.expression(Expression.property("label"))));

      Predictive Index

      Predictive Index is a new index type used for predictive query. It differs from the value index in that it caches the predictive results and creates a value index from that cache when the predictive results values are specified.

      Example 32. Creating a predictive index

      Here we create a predictive index from the label value of the prediction result.

      • Kotlin

      • Java

      val inputMap: Map<String, Any?> = mutableMapOf("numbers" to Expression.property("photo"))
collection.createIndex(
    "predictive-index-image-classifier",
    IndexBuilder.predictiveIndex("ImageClassifier", Expression.map(inputMap), null)
)
      Map<String, Object> inputMap = new HashMap<>();
inputMap.put("numbers", Expression.property("photo"));
Expression input = Expression.map(inputMap);

PredictiveIndex index = IndexBuilder.predictiveIndex("ImageClassifier", input, null);
collection.createIndex("predictive-index-image-classifier", index);

      Run a Prediction Query

      The code below creates a query that calls the prediction function to return the "label" value for the first 10 results in the database.

      Example 33. Creating a value index

      • Kotlin

      • Java

      val inputMap: Map<String, Any?> = mutableMapOf("photo" to Expression.property("photo"))
val prediction: PredictionFunction = Function.prediction(
    ImageClassifierModel.NAME,
    Expression.map(inputMap) (1)
)

val query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(
        prediction.propertyPath("label").equalTo(Expression.string("car"))
            .and(
                prediction.propertyPath("probability")
                    .greaterThanOrEqualTo(Expression.doubleValue(0.8))
            )
    )

query.execute().use {
    log("Number of rows: ${it.allResults().size}")
}
      Map<String, Object> inputProperties = new HashMap<>();
inputProperties.put("photo", Expression.property("photo"));
Expression input = Expression.map(inputProperties);
PredictionFunction prediction = Function.prediction("ImageClassifier", input); (1)

Query query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.collection(collection))
    .where(Expression.property("label").equalTo(Expression.string("car"))
        .and(prediction.propertyPath("probability").greaterThanOrEqualTo(Expression.doubleValue(0.8))));

// Run the query.
try (ResultSet result = query.execute()) {
    Logger.log("Number of rows: " + result.allResults().size());
}
      1 The PredictiveModel.predict() method returns a constructed Prediction Function object which can be used further to specify a property value extracted from the output dictionary of the PredictiveModel.predict() function.
      The null value returned by the prediction method will be interpreted as MISSING value in queries.

      Deregister the Model

      To deregister the model you must call the Database.prediction.unregisterModel static method.

      Example 34. Deregister a value index

      • Kotlin

      • Java

      Database.prediction.unregisterModel("ImageClassifier")
      Database.prediction.unregisterModel("ImageClassifier");

      Related Content

      How to . . .
      Learn more . . .
      Dive Deeper . . .

      Mobile Forum | Blog | Tutorials

      1. Starting in Couchbase Lite 2.5