GH-41834: [R] Better error handling in dplyr code#41576

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

Merged
nealrichardson merged 12 commits into from
May 29, 2024
Merged

GH-41834: [R] Better error handling in dplyr code #41576

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
5166cf7
arrow_not_supported() raises a classed error
nealrichardson May 3, 2024
4e2c735
Better distinguish invalid from not supported; add try_arrow_dplyr wr…
nealrichardson May 4, 2024
fefbc0c
More classed error raising
nealrichardson May 5, 2024
be79caa
Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr
nealrichardson May 5, 2024
66ff9c0
Rename error functions. Start updating tests
nealrichardson May 7, 2024
670e9e5
Handle assert_that and match.arg; implement alternative suggestions; …
nealrichardson May 11, 2024
0bda4e3
Add some tests, fix some tests
nealrichardson May 12, 2024
36bf23a
More test updating
nealrichardson May 25, 2024
0cd2ff3
Add more direct tests of dplyr-eval; update remaining expectations
nealrichardson May 26, 2024
df9d081
Add some cases with alternatives suggested
nealrichardson May 26, 2024
4df3a7d
Tidy up match.call
nealrichardson May 27, 2024
20e218c
Remove writing_bindings.Rmd
nealrichardson May 28, 2024
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
6 changes: 5 additions & 1 deletion r/R/dplyr-across.R
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
)

if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
arrow_not_supported(
"`...` argument to `across()` is deprecated in dplyr and",
body = c(">" = "Convert your call into a function or formula including the arguments"),

@jonkeanejonkeaneMay 27, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!

call = rlang::caller_call()
)
}

if (!is.null(across_call[[".cols"]])) {
Expand Down
87 changes: 44 additions & 43 deletions r/R/dplyr-arrange.R
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

if (.by_group) {
# when the data is grouped and .by_group is TRUE, order the result by
# the grouping columns first
exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
}
if (length(exprs) == 0) {
# Nothing to do
return(.data)
}
.data <- as_adq(.data)
# find and remove any dplyr::desc() and tidy-eval
# the arrange expressions inside an Arrow data_mask
sorts <- vector("list", length(exprs))
descs <- logical(0)
mask <- arrow_mask(.data)
for (i in seq_along(exprs)) {
x <- find_and_remove_desc(exprs[[i]])
exprs[[i]] <- x[["quos"]]
sorts[[i]] <- arrow_eval(exprs[[i]], mask)
names(sorts)[i] <- format_expr(exprs[[i]])
if (inherits(sorts[[i]], "try-error")) {
msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
return(abandon_ship(call, .data, msg))

@nealrichardsonnealrichardsonMay 27, 2024

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.

if (.by_group) {
# when the data is grouped and .by_group is TRUE, order the result by
# the grouping columns first
exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
}
if (length(mask$.aggregations)) {
# dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
# But we could, the same way it works in mutate() via join, if someone asks.
# Until then, just error.
# TODO: add a test for this
msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
return(abandon_ship(call, .data, msg))
if (length(exprs) == 0) {
# Nothing to do
return(.data)
}
descs[i] <- x[["desc"]]
}
.data$arrange_vars <- c(sorts, .data$arrange_vars)
.data$arrange_desc <- c(descs, .data$arrange_desc)
.data
.data <- as_adq(.data)
# find and remove any dplyr::desc() and tidy-eval
# the arrange expressions inside an Arrow data_mask
sorts <- vector("list", length(exprs))
descs <- logical(0)
mask <- arrow_mask(.data)
for (i in seq_along(exprs)) {
x <- find_and_remove_desc(exprs[[i]])
exprs[[i]] <- x[["quos"]]
sorts[[i]] <- arrow_eval(exprs[[i]], mask)
names(sorts)[i] <- format_expr(exprs[[i]])
if (length(mask$.aggregations)) {
# dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
# But we could, the same way it works in mutate() via join, if someone asks.
# Until then, just error.
# TODO: add a test for this
arrow_not_supported(
.actual_msg = "Expression not supported in arrange() in Arrow",
call = expr
)
}
descs[i] <- x[["desc"]]
}
.data$arrange_vars <- c(sorts, .data$arrange_vars)
.data$arrange_desc <- c(descs, .data$arrange_desc)
.data
})
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
expr <- quo_get_expr(quosure)
descending <- FALSE
if (length(all.vars(expr)) < 1L) {
stop(
"Expression in arrange() does not contain any field names: ",
deparse(expr),
call. = FALSE
validation_error(
"Expression in arrange() does not contain any field names",
call = quosure
)
}
# Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
# ensure desc() has only one argument (when an R expression is a function
# call, length == 2 means it has exactly one argument)
if (length(expr) > 2) {
stop("desc() expects only one argument", call. = FALSE)
validation_error(
"desc() expects only one argument",
call = expr
)
}
# remove desc() and toggle descending
expr <- expr[[2]]
Expand Down
31 changes: 16 additions & 15 deletions r/R/dplyr-datetime-helpers.R
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
# MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
"On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
))
arrow_not_supported(
"On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
)
}
locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

if (any(is.na(matched_chunks))) {
abort(
paste0(
"named `difftime` units other than: ",
oxford_paste(accepted_chunks, quote_symbol = "`"),
" not supported in Arrow. \nInvalid `difftime` parts: ",
arrow_not_supported(
paste(
"named `difftime` units other than:",
oxford_paste(accepted_chunks, quote_symbol = "`")
),
body = c(i = paste(
"Invalid `difftime` parts:",
oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
)
))
)
}

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

# Arrow does not support direct casting from double to date32(), but for
# integer-like values we can go via int32()
# TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

if (any(is.na(unit))) {
abort(
validation_error(
sprintf(
"Invalid period name: '%s'",
str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
# more special cases: lubridate imposes sensible maximum
# values on the number of seconds, minutes and hours
if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
}
if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
}
if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
}

list(unit = unit, multiple = multiple)
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
GH-41834: [R] Better error handling in dplyr code#41576

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

 Merged

nealrichardson
merged 12 commits into

from

May 29, 2024
 Merged


GH-41834: [R] Better error handling in dplyr code
#41576
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
5166cf7

arrow_not_supported() raises a classed error


nealrichardson May 3, 2024
4e2c735

Better distinguish invalid from not supported; add try_arrow_dplyr wr…


nealrichardson May 4, 2024
fefbc0c

More classed error raising


nealrichardson May 5, 2024
be79caa

Use cli formatting so we can add bullets; wrap more in try_arrow_dplyr


nealrichardson May 5, 2024
66ff9c0

Rename error functions. Start updating tests


nealrichardson May 7, 2024
670e9e5

Handle assert_that and match.arg; implement alternative suggestions; …


nealrichardson May 11, 2024
0bda4e3

Add some tests, fix some tests


nealrichardson May 12, 2024
36bf23a

More test updating


nealrichardson May 25, 2024
0cd2ff3

Add more direct tests of dplyr-eval; update remaining expectations


nealrichardson May 26, 2024
df9d081

Add some cases with alternatives suggested


nealrichardson May 26, 2024
4df3a7d

Tidy up match.call


nealrichardson May 27, 2024
20e218c

Remove writing_bindings.Rmd


nealrichardson May 28, 2024

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


6 changes: 5 additions & 1 deletion
r/R/dplyr-across.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,11 @@ expand_across <- function(.data, quos_in, exclude_cols = NULL) {
 )

 if (!all(names(across_call[-1]) %in% c(".cols", ".fns", ".names"))) {
 abort("`...` argument to `across()` is deprecated in dplyr and not supported in Arrow")
 arrow_not_supported(
 "`...` argument to `across()` is deprecated in dplyr and",
 body = c(">" = "Convert your call into a function or formula including the arguments"),
@jonkeanejonkeaneMay 27, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TIL about this making arrows!
 call = rlang::caller_call()
 )
 }

 if (!is.null(across_call[[".cols"]])) {
Expand Down

87 changes: 44 additions & 43 deletions
r/R/dplyr-arrange.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,47 +19,46 @@
# The following S3 methods are registered on load if dplyr is present

arrange.arrow_dplyr_query <- function(.data, ..., .by_group = FALSE) {
call <- match.call()
 .data <- as_adq(.data)
 exprs <- expand_across(.data, quos(...))
try_arrow_dplyr({
.data <- as_adq(.data)
exprs <- expand_across(.data, quos(...))

 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (inherits(sorts[[i]], "try-error")) {
 msg <- paste("Expression", names(sorts)[i], "not supported in Arrow")
 return(abandon_ship(call, .data, msg))
@nealrichardsonnealrichardsonMay 27, 2024

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here's an example of "not just an indentation change": in the new code, we don't have to evaluate, catch the error, and re-raise in abandon_ship, we just let arrow_eval() raise, and try_arrow_dplyr() handles the abandon_ship.
 if (.by_group) {
 # when the data is grouped and .by_group is TRUE, order the result by
 # the grouping columns first
 exprs <- c(quos(!!!dplyr::groups(.data)), exprs)
 }
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 msg <- paste("Expression", format_expr(expr), "not supported in arrange() in Arrow")
 return(abandon_ship(call, .data, msg))
 if (length(exprs) == 0) {
 # Nothing to do
 return(.data)
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 .data <- as_adq(.data)
 # find and remove any dplyr::desc() and tidy-eval
 # the arrange expressions inside an Arrow data_mask
 sorts <- vector("list", length(exprs))
 descs <- logical(0)
 mask <- arrow_mask(.data)
 for (i in seq_along(exprs)) {
 x <- find_and_remove_desc(exprs[[i]])
 exprs[[i]] <- x[["quos"]]
 sorts[[i]] <- arrow_eval(exprs[[i]], mask)
 names(sorts)[i] <- format_expr(exprs[[i]])
 if (length(mask$.aggregations)) {
 # dplyr lets you arrange on e.g. x < mean(x), but we haven't implemented it.
 # But we could, the same way it works in mutate() via join, if someone asks.
 # Until then, just error.
 # TODO: add a test for this
 arrow_not_supported(
 .actual_msg = "Expression not supported in arrange() in Arrow",
 call = expr
 )
 }
 descs[i] <- x[["desc"]]
 }
 .data$arrange_vars <- c(sorts, .data$arrange_vars)
 .data$arrange_desc <- c(descs, .data$arrange_desc)
 .data
 })
}
arrange.Dataset <- arrange.ArrowTabular <- arrange.RecordBatchReader <- arrange.arrow_dplyr_query

Expand All@@ -73,10 +72,9 @@ find_and_remove_desc <- function(quosure) {
 expr <- quo_get_expr(quosure)
 descending <- FALSE
 if (length(all.vars(expr)) < 1L) {
 stop(
 "Expression in arrange() does not contain any field names: ",
 deparse(expr),
 call. = FALSE
 validation_error(
 "Expression in arrange() does not contain any field names",
 call = quosure
 )
 }
 # Use a while loop to remove any number of nested pairs of enclosing
Expand All@@ -90,7 +88,10 @@ find_and_remove_desc <- function(quosure) {
 # ensure desc() has only one argument (when an R expression is a function
 # call, length == 2 means it has exactly one argument)
 if (length(expr) > 2) {
 stop("desc() expects only one argument", call. = FALSE)
 validation_error(
 "desc() expects only one argument",
 call = expr
 )
 }
 # remove desc() and toggle descending
 expr <- expr[[2]]
Expand Down

31 changes: 16 additions & 15 deletions
r/R/dplyr-datetime-helpers.R

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -18,10 +18,10 @@
check_time_locale <- function(locale = Sys.getlocale("LC_TIME")) {
 if (tolower(Sys.info()[["sysname"]]) == "windows" && locale != "C") {
 # MingW C++ std::locale only supports "C" and "POSIX"
stop(paste0(
 "On Windows, time locales other than 'C' are not supported in Arrow. ",
"Consider setting `Sys.setlocale('LC_TIME', 'C')`"
 ))
arrow_not_supported(
 "On Windows, time locales other than 'C'",
body = c(">" = "Consider setting `Sys.setlocale('LC_TIME', 'C')`")
 )
 }
 locale
}
Expand DownExpand Up@@ -56,13 +56,15 @@ duration_from_chunks <- function(chunks) {
 matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks, duplicates.ok = TRUE)]

 if (any(is.na(matched_chunks))) {
 abort(
 paste0(
 "named `difftime` units other than: ",
 oxford_paste(accepted_chunks, quote_symbol = "`"),
 " not supported in Arrow. \nInvalid `difftime` parts: ",
 arrow_not_supported(
 paste(
 "named `difftime` units other than:",
 oxford_paste(accepted_chunks, quote_symbol = "`")
 ),
 body = c(i = paste(
 "Invalid `difftime` parts:",
 oxford_paste(names(chunks[is.na(matched_chunks)]), quote_symbol = "`")
 )
 ))
 )
 }

Expand DownExpand Up@@ -114,7 +116,6 @@ binding_as_date_character <- function(x,
}

binding_as_date_numeric <- function(x, origin = "1970-01-01") {

 # Arrow does not support direct casting from double to date32(), but for
 # integer-like values we can go via int32()
 # TODO: revisit after ARROW-15798
Expand DownExpand Up@@ -442,7 +443,7 @@ parse_period_unit <- function(x) {
 unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L

 if (any(is.na(unit))) {
abort(
validation_error(
 sprintf(
 "Invalid period name: '%s'",
 str_unit,
Expand DownExpand Up@@ -484,13 +485,13 @@ parse_period_unit <- function(x) {
 # more special cases: lubridate imposes sensible maximum
 # values on the number of seconds, minutes and hours
 if (unit == 3L && multiple > 60) {
abort("Rounding with second > 60 is not supported")
validation_error("Rounding with second > 60 is not supported")
 }
 if (unit == 4L && multiple > 60) {
abort("Rounding with minute > 60 is not supported")
validation_error("Rounding with minute > 60 is not supported")
 }
 if (unit == 5L && multiple > 24) {
abort("Rounding with hour > 24 is not supported")
validation_error("Rounding with hour > 24 is not supported")
 }

 list(unit = unit, multiple = multiple)
Expand Down
Loading