Merge branch 'main' into f-join-multi-detect

krlmlr · krlmlr · commit aa07e1e25ac2 · 2025-02-01T06:21:13.000+01:00
diff --git a/R/ducktbl.R b/R/ducktbl.R
@@ -8,7 +8,7 @@
 #' dplyr verbs such as [mutate()], [select()] or [filter()]  will use DuckDB.
 #'
 #' `duckdb_tibble()` works like [tibble()], returning a lavish duckplyr data frame by default.
-#' See `vignette("funnel")` for details.
+#' See `vignette("prudence")` for details.
 #'
 #' @param ... For `duckdb_tibble()`, passed on to [tibble()].
 #'   For `as_duckdb_tibble()`, passed on to methods.
diff --git a/R/io2.R b/R/io2.R
@@ -92,7 +92,7 @@ read_json_duckdb <- function(path, ..., prudence = c("thrifty", "lavish", "fruga
 #'   `"read_csv"`, `"read_csv_auto"` or `"read_json"`.
 #' @param prudence Logical, whether to create a frugal duckplyr frame.
 #'   By default, a frugal duckplyr frame, with a limit of one million cells, is created.
-#'   See `vignette("funnel")` for details.
+#'   See `vignette("prudence")` for details.
 #' @param options Arguments to the DuckDB function
 #'   indicated by `table_function`.
 #'
diff --git a/R/prudence.R b/R/prudence.R
diff --git a/R/relational.R b/R/relational.R
@@ -132,7 +132,7 @@ check_prudence <- function(x, duckplyr_error, call = caller_env()) {
       "This operation cannot be carried out by DuckDB, and the input is a frugal duckplyr frame.",
       "*" = duckplyr_error_msg,
       "i" = 'Use {.code compute(prudence = "lavish")} to materialize to temporary storage and continue with {.pkg duckplyr}.',
-      "i" = 'See {.run vignette("funnel")} for other options.'
+      "i" = 'See {.run vignette("prudence")} for other options.'
     ))
   }
 }
diff --git a/README.Rmd b/README.Rmd
@@ -223,7 +223,7 @@ Of course, working with Parquet, CSV, or JSON files downloaded locally is possib
 
 - `vignette("large")`: Tools for working with large data
 
-- `vignette("funnel")`: How duckplyr can help protect memory when working with large data
+- `vignette("prudence")`: How duckplyr can help protect memory when working with large data
 
 - `vignette("limits")`: Translation of dplyr employed by duckplyr, and current limitations
 
diff --git a/README.md b/README.md
@@ -344,7 +344,7 @@ locally is possible as well.
 - [`vignette("large")`](https://duckplyr.tidyverse.org/dev/articles/large.html):
   Tools for working with large data
 
-- [`vignette("funnel")`](https://duckplyr.tidyverse.org/dev/articles/funnel.html):
+- [`vignette("prudence")`](https://duckplyr.tidyverse.org/dev/articles/prudence.html):
   How duckplyr can help protect memory when working with large data
 
 - [`vignette("limits")`](https://duckplyr.tidyverse.org/dev/articles/limits.html):
diff --git a/_pkgdown.yml b/_pkgdown.yml
@@ -13,7 +13,7 @@ articles:
   navbar: ~
   contents:
   - large
-  - funnel
+  - prudence
   - limits
   - developers
   - telemetry
diff --git a/index.md b/index.md
@@ -339,7 +339,7 @@ Of course, working with Parquet, CSV, or JSON files downloaded locally is possib
 
 - `vignette("large")`: Tools for working with large data
 
-- `vignette("funnel")`: How duckplyr can help protect memory when working with large data
+- `vignette("prudence")`: How duckplyr can help protect memory when working with large data
 
 - `vignette("limits")`: Translation of dplyr employed by duckplyr, and current limitations
 
diff --git a/man/duckdb_tibble.Rd b/man/duckdb_tibble.Rd
diff --git a/man/read_file_duckdb.Rd b/man/read_file_duckdb.Rd
diff --git a/man/read_sql_duckdb.Rd b/man/read_sql_duckdb.Rd
diff --git a/tests/testthat/_snaps/handle_desc.md b/tests/testthat/_snaps/handle_desc.md
@@ -6,7 +6,7 @@
       Error in `arrange()`:
       ! This operation cannot be carried out by DuckDB, and the input is a frugal duckplyr frame.
       i Use `compute(prudence = "lavish")` to materialize to temporary storage and continue with duckplyr.
-      i See `vignette("funnel")` for other options.
+      i See `vignette("prudence")` for other options.
       Caused by error in `rel_find_call()`:
       ! Function `desc` does not map to `dplyr::desc`.
 
diff --git a/tests/testthat/test-prudence.R b/tests/testthat/test-prudence.R
diff --git a/tests/testthat/test-tpch.R b/tests/testthat/test-tpch.R
@@ -8,6 +8,7 @@ test_that("TPCH queries can be parsed and run", {
     c_acctbal = numeric(0),
     c_mktsegment = character(0),
     c_comment = character(0),
+    .prudence = "frugal"
   )
 
   lineitem <- duckdb_tibble(
@@ -27,13 +28,15 @@ test_that("TPCH queries can be parsed and run", {
     l_shipinstruct = character(0),
     l_shipmode = character(0),
     l_comment = character(0),
+    .prudence = "frugal"
   )
 
   nation <- duckdb_tibble(
     n_nationkey = integer(0),
     n_name = character(0),
     n_regionkey = integer(0),
     n_comment = character(0),
+    .prudence = "frugal"
   )
 
   orders <- duckdb_tibble(
@@ -46,6 +49,7 @@ test_that("TPCH queries can be parsed and run", {
     o_clerk = character(0),
     o_shippriority = integer(0),
     o_comment = character(0),
+    .prudence = "frugal"
   )
 
   part <- duckdb_tibble(
@@ -58,6 +62,7 @@ test_that("TPCH queries can be parsed and run", {
     p_container = character(0),
     p_retailprice = numeric(0),
     p_comment = character(0),
+    .prudence = "frugal"
   )
 
   partsupp <- duckdb_tibble(
@@ -66,12 +71,14 @@ test_that("TPCH queries can be parsed and run", {
     ps_availqty = integer(0),
     ps_supplycost = numeric(0),
     ps_comment = character(0),
+    .prudence = "frugal"
   )
 
   region <- duckdb_tibble(
     r_regionkey = integer(0),
     r_name = character(0),
     r_comment = character(0),
+    .prudence = "frugal"
   )
 
   supplier <- duckdb_tibble(
@@ -82,6 +89,7 @@ test_that("TPCH queries can be parsed and run", {
     s_phone = character(0),
     s_acctbal = numeric(0),
     s_comment = character(0),
+    .prudence = "frugal"
   )
 
   withr::local_envvar(DUCKPLYR_FORCE = TRUE)
diff --git a/tools/90-patch-dplyr.R b/tools/90-patch-dplyr.R
@@ -28,7 +28,7 @@ forbidden <- fs::path("R", c(
   "zzz-methods.R",
   "duckplyr-package.R",
   "fallback.R",
-  "funnel.R",
+  "prudence.R",
   "head.R",
   "meta.R",
   "n-col.R",
diff --git a/vignettes/developers.Rmd b/vignettes/developers.Rmd
@@ -133,4 +133,4 @@ data
 nrow(data)
 ```
 
-Learn more about prudence in `vignette("funnel")`, and about the translation employed by duckplyr in `vignette("limits")`.
+Learn more about prudence in `vignette("prudence")`, and about the translation employed by duckplyr in `vignette("limits")`.
diff --git a/vignettes/large.Rmd b/vignettes/large.Rmd
@@ -67,7 +67,7 @@ Full compatibility means fewer surprises and less cognitive load for the user.
 With DuckDB as the backend, duckplyr can also handle large data sets that do not fit into RAM, keeping full dplyr compatibility.
 The tools for bringing data into and out of R memory are modeled after the dplyr and dbplyr packages, and are described in the following sections.
 
-See `vignette("funnel")` on eager and lazy data, `vignette("limits")` for limitations in the translation employed by duckplyr, and `?fallback` for more information on fallback.
+See `vignette("prudence")` on eager and lazy data, `vignette("limits")` for limitations in the translation employed by duckplyr, and `?fallback` for more information on fallback.
 
 
 ## To duckplyr
@@ -177,7 +177,7 @@ flights_parquet
 In all cases, the data is read lazily: only the metadata is read initially, and the data is read as required.
 This means that data can be read from files that are larger than the available RAM.
 The Parquet format is particularly efficient for this purpose, as it stores data in a columnar format and allows reading only the columns that are required.
-See `vignette("funnel")` for more details on the concept of lazy data.
+See `vignette("prudence")` for more details on the concept of lazy data.
 
 ## From DuckDB
 
@@ -305,4 +305,4 @@ flights_parquet |>
   group_by(Month)
 ```
 
-See `vignette("funnel")` for the concepts and mechanisms at play.
+See `vignette("prudence")` for the concepts and mechanisms at play.
diff --git a/vignettes/prudence.Rmd b/vignettes/prudence.Rmd
@@ -105,7 +105,8 @@ system.time(mean_arr_delay_ewr$mean_arr_delay[[1]])
 
 ### Comparison
 
-The functionality is similar to lazy tables in dbplyr and lazy frames in dtplyr. However, the behavior is different: at the time of writing, the internal structure of a lazy table or frame is different from a data frame, and columns cannot be accessed directly.
+The functionality is similar to lazy tables in dbplyr and lazy frames in dtplyr.
+However, the behavior is different: at the time of writing, the internal structure of a lazy table or frame is different from a data frame, and columns cannot be accessed directly.
 
 |             | **Eager** 😃 | **Lazy** 😴 |
 |-------------|:------------:|:-----------:|
@@ -130,6 +131,7 @@ system.time(
 )
 ```
 
+See also the [duckplyr: dplyr Powered by DuckDB](https://duckdb.org/2024/04/02/duckplyr.html) blog post for more information.
 
 ## Prudence
 

Original file line number	Diff line number	Diff line change
`@@ -132,7 +132,7 @@ check_prudence <- function(x, duckplyr_error, call = caller_env()) {`
`132`	`132`	`"This operation cannot be carried out by DuckDB, and the input is a frugal duckplyr frame.",`
`133`	`133`	`"*" = duckplyr_error_msg,`
`134`	`134`	`"i" = 'Use {.code compute(prudence = "lavish")} to materialize to temporary storage and continue with {.pkg duckplyr}.',`
`135`		`- "i" = 'See {.run vignette("funnel")} for other options.'`
	`135`	`+ "i" = 'See {.run vignette("prudence")} for other options.'`
`136`	`136`	`))`
`137`	`137`	`}`
`138`	`138`	`}`