This is an automated email from the ASF dual-hosted git repository.
lidavidm pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-adbc.git
The following commit(s) were added to refs/heads/main by this push:
new aa1990bb1 docs(r): Update READMEs for R packages (#1707)
aa1990bb1 is described below
commit aa1990bb155f053b8ed4e20b49b04421a0c8a205
Author: Dewey Dunnington <[email protected]>
AuthorDate: Wed Apr 3 17:26:53 2024 -0300
docs(r): Update READMEs for R packages (#1707)
Just a pass through all the READMEs to generally align them with how
people are most likely to interact with them at first glance!
---
r/adbcdrivermanager/README.Rmd | 29 +++++++++--------------------
r/adbcdrivermanager/README.md | 38 ++++++++++++++------------------------
r/adbcpostgresql/README.Rmd | 10 +++-------
r/adbcpostgresql/README.md | 18 +++++++-----------
r/adbcsqlite/README.Rmd | 22 +++++++++-------------
r/adbcsqlite/README.md | 28 ++++++++++++----------------
6 files changed, 54 insertions(+), 91 deletions(-)
diff --git a/r/adbcdrivermanager/README.Rmd b/r/adbcdrivermanager/README.Rmd
index 439268cb8..4384c8b4a 100644
--- a/r/adbcdrivermanager/README.Rmd
+++ b/r/adbcdrivermanager/README.Rmd
@@ -70,33 +70,22 @@ library(adbcdrivermanager)
# Get a reference to a database using a driver. The adbcdrivermanager package
# contains a few drivers useful for illustration and testing.
-db <- adbc_database_init(adbc_driver_monkey())
+db <- adbc_database_init(adbcsqlite::adbcsqlite())
# Open a new connection to a database
con <- adbc_connection_init(db)
-# Initialize a new statement from a connection
-stmt <- adbc_statement_init(con)
+# Write a table
+nycflights13::flights |> write_adbc(con, "flights")
-# The monkey driver allows you to specify the data for a query
-# in advance for testing purposes
-adbc_statement_bind_stream(stmt, nycflights13::flights)
-
-# Set the query
-adbc_statement_set_sql_query(stmt, "SELECT * FROM flights")
-
-# Start executing the query. Results in ADBC are ArrowArrayStream objects,
-# which can be materialized using as.data.frame(), as_tibble(),
-# or converted to an arrow::RecordBatchReader using
-# arrow::as_record_batch_reader()
-stream <- nanoarrow::nanoarrow_allocate_array_stream()
-adbc_statement_execute_query(stmt, stream)
-
-# Materialize the whole query as a tibble
-tibble::as_tibble(stream)
+# Issue a query
+con |>
+ read_adbc("SELECT * from flights") |>
+ tibble::as_tibble()
# Clean up!
-adbc_statement_release(stmt)
adbc_connection_release(con)
adbc_database_release(db)
```
+
+One can also interact with the driver manager at a lower level using
`adbc_connection_*()` and `adbc_statement_*()` functions (see reference
documentation for details).
diff --git a/r/adbcdrivermanager/README.md b/r/adbcdrivermanager/README.md
index 231fc8a48..387f64c2f 100644
--- a/r/adbcdrivermanager/README.md
+++ b/r/adbcdrivermanager/README.md
@@ -62,34 +62,21 @@ library(adbcdrivermanager)
# Get a reference to a database using a driver. The adbcdrivermanager package
# contains a few drivers useful for illustration and testing.
-db <- adbc_database_init(adbc_driver_monkey())
+db <- adbc_database_init(adbcsqlite::adbcsqlite())
# Open a new connection to a database
con <- adbc_connection_init(db)
-# Initialize a new statement from a connection
-stmt <- adbc_statement_init(con)
+# Write a table
+nycflights13::flights |> write_adbc(con, "flights")
-# The monkey driver allows you to specify the data for a query
-# in advance for testing purposes
-adbc_statement_bind_stream(stmt, nycflights13::flights)
-
-# Set the query
-adbc_statement_set_sql_query(stmt, "SELECT * FROM flights")
-
-# Start executing the query. Results in ADBC are ArrowArrayStream objects,
-# which can be materialized using as.data.frame(), as_tibble(),
-# or converted to an arrow::RecordBatchReader using
-# arrow::as_record_batch_reader()
-stream <- nanoarrow::nanoarrow_allocate_array_stream()
-adbc_statement_execute_query(stmt, stream)
-#> [1] -1
-
-# Materialize the whole query as a tibble
-tibble::as_tibble(stream)
+# Issue a query
+con |>
+ read_adbc("SELECT * from flights") |>
+ tibble::as_tibble()
#> # A tibble: 336,776 × 19
#> year month day dep_time sched_dep_time dep_delay arr_time
sched_arr_time
-#> <int> <int> <int> <int> <int> <dbl> <int>
<int>
+#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
<dbl>
#> 1 2013 1 1 517 515 2 830
819
#> 2 2013 1 1 533 529 4 850
830
#> 3 2013 1 1 542 540 2 923
850
@@ -101,12 +88,15 @@ tibble::as_tibble(stream)
#> 9 2013 1 1 557 600 -3 838
846
#> 10 2013 1 1 558 600 -2 753
745
#> # ℹ 336,766 more rows
-#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
+#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <dbl>,
#> # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
-#> # hour <dbl>, minute <dbl>, time_hour <dttm>
+#> # hour <dbl>, minute <dbl>, time_hour <chr>
# Clean up!
-adbc_statement_release(stmt)
adbc_connection_release(con)
adbc_database_release(db)
```
+
+One can also interact with the driver manager at a lower level using
+`adbc_connection_*()` and `adbc_statement_*()` functions (see reference
+documentation for details).
diff --git a/r/adbcpostgresql/README.Rmd b/r/adbcpostgresql/README.Rmd
index cc68887b2..b94915c16 100644
--- a/r/adbcpostgresql/README.Rmd
+++ b/r/adbcpostgresql/README.Rmd
@@ -73,20 +73,16 @@ db <- adbc_database_init(adbcpostgresql::adbcpostgresql(),
uri = uri)
con <- adbc_connection_init(db)
# Write a table
-flights <- head(nycflights13::flights, 100)
-# (timestamp not supported yet)
-flights$time_hour <- NULL
-flights |>
- write_adbc(con, "flights")
+nycflights13::flights |> write_adbc(con, "flights")
-# Query it
+# Issue a query
con |>
read_adbc("SELECT * from flights") |>
tibble::as_tibble()
```
```{r example-clean-up}
-# Clean up
+# Clean up!
con |>
execute_adbc("DROP TABLE flights")
adbc_connection_release(con)
diff --git a/r/adbcpostgresql/README.md b/r/adbcpostgresql/README.md
index b902cc8c1..96112aada 100644
--- a/r/adbcpostgresql/README.md
+++ b/r/adbcpostgresql/README.md
@@ -64,17 +64,13 @@ db <- adbc_database_init(adbcpostgresql::adbcpostgresql(),
uri = uri)
con <- adbc_connection_init(db)
# Write a table
-flights <- head(nycflights13::flights, 100)
-# (timestamp not supported yet)
-flights$time_hour <- NULL
-flights |>
- write_adbc(con, "flights")
+nycflights13::flights |> write_adbc(con, "flights")
-# Query it
+# Issue a query
con |>
read_adbc("SELECT * from flights") |>
tibble::as_tibble()
-#> # A tibble: 100 × 18
+#> # A tibble: 336,776 × 19
#> year month day dep_time sched_dep_time dep_delay arr_time
sched_arr_time
#> <int> <int> <int> <int> <int> <dbl> <int>
<int>
#> 1 2013 1 1 517 515 2 830
819
@@ -87,14 +83,14 @@ con |>
#> 8 2013 1 1 557 600 -3 709
723
#> 9 2013 1 1 557 600 -3 838
846
#> 10 2013 1 1 558 600 -2 753
745
-#> # ℹ 90 more rows
-#> # ℹ 10 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
+#> # ℹ 336,766 more rows
+#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
#> # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
-#> # hour <dbl>, minute <dbl>
+#> # hour <dbl>, minute <dbl>, time_hour <dttm>
```
``` r
-# Clean up
+# Clean up!
con |>
execute_adbc("DROP TABLE flights")
adbc_connection_release(con)
diff --git a/r/adbcsqlite/README.Rmd b/r/adbcsqlite/README.Rmd
index ffcaee358..950e97e46 100644
--- a/r/adbcsqlite/README.Rmd
+++ b/r/adbcsqlite/README.Rmd
@@ -67,27 +67,23 @@ This is a basic example which shows you how to solve a
common problem:
```{r example}
library(adbcdrivermanager)
-# Use the driver manager to connect to a database
-db <- adbc_database_init(adbcsqlite::adbcsqlite(), uri = ":memory:")
+# Open a new connection to a database
+db <- adbc_database_init(
+ adbcsqlite::adbcsqlite(),
+ uri = ":memory:"
+)
+
con <- adbc_connection_init(db)
# Write a table
-flights <- nycflights13::flights
-# (timestamp not supported yet)
-flights$time_hour <- NULL
-flights |>
- write_adbc(con, "flights")
+nycflights13::flights |> write_adbc(con, "flights")
-# Query it
+# Issue a query
con |>
read_adbc("SELECT * from flights") |>
tibble::as_tibble()
-```
-```{r}
-# Clean up
-con |>
- execute_adbc("DROP TABLE flights")
+# Clean up!
adbc_connection_release(con)
adbc_database_release(db)
```
diff --git a/r/adbcsqlite/README.md b/r/adbcsqlite/README.md
index f04f07cbe..9fc8e5d24 100644
--- a/r/adbcsqlite/README.md
+++ b/r/adbcsqlite/README.md
@@ -58,22 +58,22 @@ This is a basic example which shows you how to solve a
common problem:
``` r
library(adbcdrivermanager)
-# Use the driver manager to connect to a database
-db <- adbc_database_init(adbcsqlite::adbcsqlite(), uri = ":memory:")
+# Open a new connection to a database
+db <- adbc_database_init(
+ adbcsqlite::adbcsqlite(),
+ uri = ":memory:"
+)
+
con <- adbc_connection_init(db)
# Write a table
-flights <- nycflights13::flights
-# (timestamp not supported yet)
-flights$time_hour <- NULL
-flights |>
- write_adbc(con, "flights")
+nycflights13::flights |> write_adbc(con, "flights")
-# Query it
+# Issue a query
con |>
read_adbc("SELECT * from flights") |>
tibble::as_tibble()
-#> # A tibble: 336,776 × 18
+#> # A tibble: 336,776 × 19
#> year month day dep_time sched_dep_time dep_delay arr_time
sched_arr_time
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
<dbl>
#> 1 2013 1 1 517 515 2 830
819
@@ -87,15 +87,11 @@ con |>
#> 9 2013 1 1 557 600 -3 838
846
#> 10 2013 1 1 558 600 -2 753
745
#> # ℹ 336,766 more rows
-#> # ℹ 10 more variables: arr_delay <dbl>, carrier <chr>, flight <dbl>,
+#> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <dbl>,
#> # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
-#> # hour <dbl>, minute <dbl>
-```
+#> # hour <dbl>, minute <dbl>, time_hour <chr>
-``` r
-# Clean up
-con |>
- execute_adbc("DROP TABLE flights")
+# Clean up!
adbc_connection_release(con)
adbc_database_release(db)
```
