% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/verb-joins.R
\name{join.tbl_sql}
\alias{join.tbl_sql}
\alias{inner_join.tbl_lazy}
\alias{left_join.tbl_lazy}
\alias{right_join.tbl_lazy}
\alias{full_join.tbl_lazy}
\alias{semi_join.tbl_lazy}
\alias{anti_join.tbl_lazy}
\title{Join SQL tables}
\usage{
\method{inner_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  suffix = NULL,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)

\method{left_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  suffix = NULL,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)

\method{right_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  suffix = NULL,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)

\method{full_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  suffix = NULL,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)

\method{semi_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)

\method{anti_join}{tbl_lazy}(
  x,
  y,
  by = NULL,
  copy = FALSE,
  auto_index = FALSE,
  ...,
  sql_on = NULL,
  na_matches = c("never", "na"),
  x_as = NULL,
  y_as = NULL
)
}
\arguments{
\item{x, y}{A pair of lazy data frames backed by database queries.}

\item{by}{A character vector of variables to join by.

If \code{NULL}, the default, \verb{*_join()} will perform a natural join, using all
variables in common across \code{x} and \code{y}. A message lists the variables so that you
can check they're correct; suppress the message by supplying \code{by} explicitly.

To join by different variables on \code{x} and \code{y}, use a named vector.
For example, \code{by = c("a" = "b")} will match \code{x$a} to \code{y$b}.

To join by multiple variables, use a vector with length > 1.
For example, \code{by = c("a", "b")} will match \code{x$a} to \code{y$a} and \code{x$b} to
\code{y$b}. Use a named vector to match different variables in \code{x} and \code{y}.
For example, \code{by = c("a" = "b", "c" = "d")} will match \code{x$a} to \code{y$b} and
\code{x$c} to \code{y$d}.

To perform a cross-join, generating all combinations of \code{x} and \code{y},
use \code{by = character()}.}

\item{copy}{If \code{x} and \code{y} are not from the same data source,
and \code{copy} is \code{TRUE}, then \code{y} will be copied into a
temporary table in same database as \code{x}. \verb{*_join()} will automatically
run \code{ANALYZE} on the created table in the hope that this will make
you queries as efficient as possible by giving more data to the query
planner.

This allows you to join tables across srcs, but it's potentially expensive
operation so you must opt into it.}

\item{suffix}{If there are non-joined duplicate variables in \code{x} and
\code{y}, these suffixes will be added to the output to disambiguate them.
Should be a character vector of length 2.}

\item{auto_index}{if \code{copy} is \code{TRUE}, automatically create
indices for the variables in \code{by}. This may speed up the join if
there are matching indexes in \code{x}.}

\item{...}{Other parameters passed onto methods.}

\item{sql_on}{A custom join predicate as an SQL expression.
Usually joins use column equality, but you can perform more complex
queries by supply \code{sql_on} which should be a SQL expression that
uses \code{LHS} and \code{RHS} aliases to refer to the left-hand side or
right-hand side of the join respectively.}

\item{na_matches}{Should NA (NULL) values match one another?
The default, "never", is how databases usually work. \code{"na"} makes
the joins behave like the dplyr join functions, \code{\link[=merge]{merge()}}, \code{\link[=match]{match()}},
and \code{\%in\%}.}

\item{x_as, y_as}{Alias to use for \code{x} resp. \code{y}. Defaults to \code{"LHS"} resp.
\code{"RHS"}}
}
\value{
Another \code{tbl_lazy}. Use \code{\link[=show_query]{show_query()}} to see the generated
query, and use \code{\link[=collect.tbl_sql]{collect()}} to execute the query
and return data to R.
}
\description{
These are methods for the dplyr \link{join} generics. They are translated
to the following SQL queries:
\itemize{
\item \code{inner_join(x, y)}: \verb{SELECT * FROM x JOIN y ON x.a = y.a}
\item \code{left_join(x, y)}:  \verb{SELECT * FROM x LEFT JOIN y ON x.a = y.a}
\item \code{right_join(x, y)}: \verb{SELECT * FROM x RIGHT JOIN y ON x.a = y.a}
\item \code{full_join(x, y)}:  \verb{SELECT * FROM x FULL JOIN y ON x.a = y.a}
\item \code{semi_join(x, y)}:  \verb{SELECT * FROM x WHERE EXISTS (SELECT 1 FROM y WHERE x.a = y.a)}
\item \code{anti_join(x, y)}:  \verb{SELECT * FROM x WHERE NOT EXISTS (SELECT 1 FROM y WHERE x.a = y.a)}
}
}
\examples{
library(dplyr, warn.conflicts = FALSE)

band_db <- tbl_memdb(dplyr::band_members)
instrument_db <- tbl_memdb(dplyr::band_instruments)
band_db \%>\% left_join(instrument_db) \%>\% show_query()

# Can join with local data frames by setting copy = TRUE
band_db \%>\%
  left_join(dplyr::band_instruments, copy = TRUE)

# Unlike R, joins in SQL don't usually match NAs (NULLs)
db <- memdb_frame(x = c(1, 2, NA))
label <- memdb_frame(x = c(1, NA), label = c("one", "missing"))
db \%>\% left_join(label, by = "x")
# But you can activate R's usual behaviour with the na_matches argument
db \%>\% left_join(label, by = "x", na_matches = "na")

# By default, joins are equijoins, but you can use `sql_on` to
# express richer relationships
db1 <- memdb_frame(x = 1:5)
db2 <- memdb_frame(x = 1:3, y = letters[1:3])
db1 \%>\% left_join(db2) \%>\% show_query()
db1 \%>\% left_join(db2, sql_on = "LHS.x < RHS.x") \%>\% show_query()
}