') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); ARROW-16394: [R] Implement lubridate's parsers with year, month and date components by dragosmg · Pull Request #13118 · apache/arrow · GitHub
Skip to content

ARROW-16394: [R] Implement lubridate's parsers with year, month and date components#13118

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

Closed
dragosmg wants to merge 6 commits into from
Closed

ARROW-16394: [R] Implement lubridate's parsers with year, month and date components #13118

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
edfa6ed
added year, month, and day parsers + unit tests
dragosmg May 11, 2022
4c5677d
lint
dragosmg May 11, 2022
33463a6
skip tests on win & r 3.6
dragosmg May 11, 2022
2172c0b
added comment about casting to `date32()` when `tz` is `NULL`
dragosmg May 12, 2022
1d7fce9
added comment on why we need to handle a situation when `tz` is `NULL…
dragosmg May 12, 2022
2f8bbd9
update comment
dragosmg May 12, 2022
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
30 changes: 29 additions & 1 deletion r/R/dplyr-funcs-datetime.R
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -518,6 +518,34 @@ register_bindings_datetime_parsers <- function() {

coalesce_output <- build_expr("coalesce", args = parse_attempt_expressions)

build_expr("assume_timezone", coalesce_output, options = list(timezone = tz))
# we need this binding to be able to handle a NULL `tz`, which will then be
# used by bindings such as `ymd` to return, based on whether tz is NULL or
# not, a date or timestamp
if (!is.null(tz)) {
Comment thread
dragosmg marked this conversation as resolved.
build_expr("assume_timezone", coalesce_output, options = list(timezone = tz))
} else {
coalesce_output
}

})

ymd_parser_vec <- c("ymd", "ydm", "mdy", "myd", "dmy", "dym")

ymd_parser_map_factory <- function(order) {
force(order)
Comment thread
dragosmg marked this conversation as resolved.
function(x, tz = NULL) {
parse_x <- call_binding("parse_date_time", x, order, tz)
if (is.null(tz)) {
# we cast so we can mimic the behaviour of the `tz` argument in lubridate
# "If NULL (default), a Date object is returned. Otherwise a POSIXct with
# time zone attribute set to tz."
parse_x <- parse_x$cast(date32())
Comment thread
dragosmg marked this conversation as resolved.
}
parse_x
}
}

for (ymd_order in ymd_parser_vec) {
register_binding(ymd_order, ymd_parser_map_factory(ymd_order))
}
}
50 changes: 47 additions & 3 deletions r/tests/testthat/test-dplyr-funcs-datetime.R
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1254,7 +1254,7 @@ test_that("`decimal_date()` and `date_decimal()`", {
mutate(
decimal_date_from_POSIXct = decimal_date(b),
decimal_date_from_r_POSIXct_obj = decimal_date(as.POSIXct("2022-03-25 15:37:01")),
decimal_date_from_r_date_obj = decimal_date(ymd("2022-03-25")),
decimal_date_from_r_date_obj = decimal_date(as.Date("2022-03-25")),
decimal_date_from_date = decimal_date(c),
date_from_decimal = date_decimal(a),
date_from_decimal_r_obj = date_decimal(2022.178)
Expand DownExpand Up@@ -1640,7 +1640,8 @@ test_that("`as_datetime()`", {
})

test_that("parse_date_time() works with year, month, and date components", {
# string processing requires RE2 library (not available on Windows with R 3.6)
# these functions' internals use some string processing which requires the
# RE2 library (not available on Windows with R 3.6)
skip_if_not_available("re2")
compare_dplyr_binding(
.input %>%
Expand DownExpand Up@@ -1700,7 +1701,8 @@ test_that("parse_date_time() works with year, month, and date components", {
})

test_that("parse_date_time() works with a mix of formats and orders", {
# string processing requires RE2 library (not available on Windows with R 3.6)
# these functions' internals use some string processing which requires the
# RE2 library (not available on Windows with R 3.6)
skip_if_not_available("re2")
test_df <- tibble(
string_combi = c("2021-09-1", "2/09//2021", "09.3.2021")
Expand DownExpand Up@@ -1732,3 +1734,45 @@ test_that("parse_date_time() doesn't work with hour, minutes, and second compone
'"ymd_HMS" `orders` not supported in Arrow'
)
})

test_that("year, month, day date/time parsers work", {
test_df <- tibble::tibble(
ymd_string = c("2022-05-11", "2022/05/12", "22.05-13"),
ydm_string = c("2022-11-05", "2022/12/05", "22.13-05"),
mdy_string = c("05-11-2022", "05/12/2022", "05.13-22"),
myd_string = c("05-2022-11", "05/2022/12", "05.22-14"),
dmy_string = c("11-05-2022", "12/05/2022", "13.05-22"),
dym_string = c("11-2022-05", "12/2022/05", "13.22-05")
)

# these functions' internals use some string processing which requires the
# RE2 library (not available on Windows with R 3.6)
skip_if_not_available("re2")
compare_dplyr_binding(
.input %>%
mutate(
ymd_date = ymd(ymd_string),
ydm_date = ydm(ydm_string),
mdy_date = mdy(mdy_string),
myd_date = myd(myd_string),
dmy_date = dmy(dmy_string),
dym_date = dym(dym_string)
) %>%
collect(),
test_df
)

compare_dplyr_binding(
.input %>%
mutate(
ymd_date = ymd(ymd_string, tz = "Pacific/Marquesas"),
ydm_date = ydm(ydm_string, tz = "Pacific/Marquesas"),
mdy_date = mdy(mdy_string, tz = "Pacific/Marquesas"),
myd_date = myd(myd_string, tz = "Pacific/Marquesas"),
dmy_date = dmy(dmy_string, tz = "Pacific/Marquesas"),
dym_date = dym(dym_string, tz = "Pacific/Marquesas")
) %>%
collect(),
test_df
)
})