Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Order-stable union_all() #45

Merged
merged 3 commits into from
Sep 7, 2023
Merged

feat: Order-stable union_all() #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9703f2d
Add dots
krlmlr Sep 6, 2023
349192f
Order-stable union_all()
krlmlr Sep 6, 2023
35345bb
Add duckdb remote
krlmlr Sep 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ Imports:
collections,
DBI,
dplyr (>= 1.1.3),
duckdb (>= 0.8.1-3),
duckdb (>= 0.8.1-9000),
glue,
lifecycle,
purrr,
Expand All @@ -46,6 +46,8 @@ Suggests:
styler,
testthat (>= 3.1.5),
withr
Remotes:
duckdb=duckdb/duckdb-r
Config/testthat/edition: 3
Config/testthat/parallel: false
Config/testthat/start-first: as_duckplyr_df, mutate, filter, count-tally
Expand Down
26 changes: 20 additions & 6 deletions R/oo.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,15 @@ oo_force <- function() {
return(FALSE)
}

oo_prep <- function(rel, colname = "___row_number", force = oo_force()) {
oo_prep <- function(
rel,
colname = "___row_number",
...,
extra_cols_pre = character(),
extra_cols_post = character(),
force = oo_force()) {
check_dots_empty0(...)

if (!force) {
return(rel)
}
Expand All @@ -22,11 +30,17 @@ oo_prep <- function(rel, colname = "___row_number", force = oo_force()) {
}

proj_exprs <- imap(set_names(names), relexpr_reference, rel = NULL)
proj_exprs <- c(proj_exprs, list(relexpr_window(
relexpr_function("row_number", list()),
partitions = list(),
alias = colname
)))
proj_exprs <- c(
proj_exprs,
if (length(extra_cols_pre)) map(extra_cols_pre, relexpr_constant, val = NA_integer_),
list(relexpr_window(
relexpr_function("row_number", list()),
partitions = list(),
alias = colname
)),
if (length(extra_cols_post)) map(extra_cols_post, relexpr_constant, val = NA_integer_),
NULL
)

rel_project(rel, unname(proj_exprs))
}
Expand Down
7 changes: 7 additions & 0 deletions R/union_all.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,14 @@ union_all.duckplyr_df <- function(x, y, ...) {
y_rel <- rel_project(y_rel, exprs)
}

x_rel <- oo_prep(x_rel, "___row_number_x", extra_cols_post = "___row_number_y")
y_rel <- oo_prep(y_rel, "___row_number_y", extra_cols_pre = "___row_number_x")

rel <- rel_union_all(x_rel, y_rel)

# NULLs sort first in duckdb!
rel <- oo_restore(rel, c("___row_number_x", "___row_number_y"))

out <- rel_to_df(rel)
out <- dplyr_reconstruct(out, x)
return(out)
Expand Down
11 changes: 9 additions & 2 deletions patch/union_all.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
diff --git b/R/union_all.R a/R/union_all.R
index ed860f1..0279a26 100644
index ed860f1..727b739 100644
--- b/R/union_all.R
+++ a/R/union_all.R
@@ -2,9 +2,31 @@
@@ -2,9 +2,38 @@
#' @export
union_all.duckplyr_df <- function(x, y, ...) {
# Our implementation
Expand All @@ -29,7 +29,14 @@ index ed860f1..0279a26 100644
+ y_rel <- rel_project(y_rel, exprs)
+ }
+
+ x_rel <- oo_prep(x_rel, "___row_number_x", extra_cols_post = "___row_number_y")
+ y_rel <- oo_prep(y_rel, "___row_number_y", extra_cols_pre = "___row_number_x")
+
+ rel <- rel_union_all(x_rel, y_rel)
+
+ # NULLs sort first in duckdb!
+ rel <- oo_restore(rel, c("___row_number_x", "___row_number_y"))
+
+ out <- rel_to_df(rel)
+ out <- dplyr_reconstruct(out, x)
return(out)
Expand Down
Loading