Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Jump to bottom

Fix Windows Parsing Issue #6150

Merged
merged 7 commits into from
May 27, 2024
Merged

Fix Windows Parsing Issue #6150

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
800d787
refactor tests to no longer use explicit japanese characters, surroun…
joshhwuu May 22, 2024
5cde4a5
wrap failing tests to use utf8 locale
joshhwuu May 26, 2024
8cab214
Merge branch 'master' into fixwindowsparse
joshhwuu May 26, 2024
c20ccab
remove trailing whitespaces
joshhwuu May 26, 2024
3f50bae
Merge branch 'fixwindowsparse' of https://github.com/Rdatatable/data.…
joshhwuu May 26, 2024
a9cea9d
review suggestions
joshhwuu May 27, 2024
5eb7e04
move strrep to top of file
joshhwuu May 27, 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
95 changes: 57 additions & 38 deletions inst/tests/tests.Rraw
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,11 @@ with_c_collate = function(expr) {
expr
}

# strrep is used many times in tests, but is from R 3.3.0, so use this equivalent if it is missing.
if (!exists("strrep", "package:base")) {
strrep = function(x, times) mapply(function(x, times) paste(rep(x, times), collapse=""), rep_len(x, length(times)), times, USE.NAMES=FALSE)
}

##########################
.do_not_rm = ls() # objects that exist at this point should not be removed by rm_all(); e.g. test_*, base_messages, Ctest_dt_win_snprintf, prevtest, etc
##########################
Expand Down Expand Up @@ -18428,44 +18433,58 @@ test(2252.2, dt[, let(b=2L)], error = "\\[ was called on a data.table.*not data.
rm(.datatable.aware)

# tests for trunc.char handling wide characters # 5096
accented_a = "\u0061\u0301"
ja_ichi = "\u4E00"
ja_ni = "\u4E8C"
ja_ko = "\u3053"
ja_n = "\u3093"
dots = "..."
clean_regex = "^\\d+:\\s+" # removes row numbering from beginning of output
# Tests for combining character latin a and acute accent, single row
DT = data.table(strrep(accented_a, 4L))
test(2253.01, options=list(datatable.prettyprint.char = 4L), DT, output=strrep(accented_a, 4L))
test(2253.02, options=list(datatable.prettyprint.char = 3L), DT, output=paste0(strrep(accented_a, 3L), dots))
test(2253.03, options=list(datatable.prettyprint.char = 1L), DT, output=paste0(strrep(accented_a, 1L), dots))
# Tests for full-width japanese character ichi, single row
DT = data.table(strrep(ja_ichi, 4L))
test(2253.04, options=list(datatable.prettyprint.char = 4L), DT, output=strrep(ja_ichi, 4L))
test(2253.05, options=list(datatable.prettyprint.char = 3L), DT, output=paste0(strrep(ja_ichi, 3L), dots))
test(2253.06, options=list(datatable.prettyprint.char = 1L), DT, output=paste0(strrep(ja_ichi, 1L), dots))
# Tests for multiple, different length combining character rows
DT = data.table(strrep(accented_a, 1L:4L))
test(2253.07, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("á", "áá", "ááá", "áááá"))
test(2253.08, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("á", "áá", "ááá", "ááá..."))
test(2253.09, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("á", "á...", "á...", "á..."))
# Tests for multiple, different length full-width characters
DT = data.table(strrep(ja_ichi, 1L:4L))
test(2253.10, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("一", "一一", "一一一", "一一一一"))
test(2253.11, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("一", "一一", "一一一", "一一一..."))
test(2253.12, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("一", "一...", "一...", "一..."))
# Tests for combined characters, multiple columns
DT = data.table(paste0(ja_ichi), strrep(ja_ni, 2L), strrep(ja_ko, 3L), strrep(accented_a, 2L), "aaa")
test(2253.13, options=list(datatable.prettyprint.char = 4L), capture.output(print(DT))[-1L], "1: 一 二二 こここ áá aaa")
test(2253.14, options=list(datatable.prettyprint.char = 3L), capture.output(print(DT))[-1L], "1: 一 二二 こここ áá aaa")
test(2253.15, options=list(datatable.prettyprint.char = 2L), capture.output(print(DT))[-1L], "1: 一 二二 ここ... áá aa...")
test(2253.16, options=list(datatable.prettyprint.char = 1L), capture.output(print(DT))[-1L], "1: 一 二... こ... á... a...")
# Tests for multiple columns, multiple rows
DT = data.table(strrep(ja_ko, 1:3L), strrep(ja_n, 2:4L), strrep(accented_a, 3))
test(2253.17, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("こ んん ááá", "ここ んんん ááá", "こここ んんんん ááá"))
test(2253.18, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("こ んん ááá", "ここ んんん ááá", "こここ んんん... ááá"))
test(2253.19, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c("こ ん... á...", "こ... ん... á...", "こ... ん... á..."))
local({
lc_ctype = Sys.getlocale('LC_CTYPE')
Sys.setlocale('LC_CTYPE', "en_US.UTF-8") # Japanese multibyte characters require utf8
on.exit({Sys.setlocale('LC_CTYPE', lc_ctype)})
accented_a = "\u0061\u0301"
ja_ichi = "\u4E00"
ja_ni = "\u4E8C"
ja_ko = "\u3053"
ja_n = "\u3093"
dots = "..."
clean_regex = "^\\d+:\\s+" # removes row numbering from beginning of output
# Tests for combining character latin a and acute accent, single row
DT = data.table(strrep(accented_a, 4L))
test(2253.01, options=list(datatable.prettyprint.char = 4L), DT, output=strrep(accented_a, 4L))
test(2253.02, options=list(datatable.prettyprint.char = 3L), DT, output=paste0(strrep(accented_a, 3L), dots))
test(2253.03, options=list(datatable.prettyprint.char = 1L), DT, output=paste0(strrep(accented_a, 1L), dots))
# Tests for full-width japanese character ichi, single row
DT = data.table(strrep(ja_ichi, 4L))
test(2253.04, options=list(datatable.prettyprint.char = 4L), DT, output=strrep(ja_ichi, 4L))
joshhwuu marked this conversation as resolved.
Show resolved Hide resolved
test(2253.05, options=list(datatable.prettyprint.char = 3L), DT, output=paste0(strrep(ja_ichi, 3L), dots))
test(2253.06, options=list(datatable.prettyprint.char = 1L), DT, output=paste0(strrep(ja_ichi, 1L), dots))
# Tests for multiple, different length combining character rows
DT = data.table(strrep(accented_a, 1L:4L))
test(2253.07, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), strrep(accented_a, 1:4L))
test(2253.08, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c(strrep(accented_a, 1:3), paste0(strrep(accented_a, 3L), dots)))
test(2253.09, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c(accented_a, rep(paste0(accented_a, dots), 3L)))
# Tests for multiple, different length full-width characters
DT = data.table(strrep(ja_ichi, 1L:4L))
test(2253.10, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), strrep(ja_ichi, 1:4L))
test(2253.11, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c(strrep(ja_ichi, 1:3), paste0(strrep(ja_ichi, 3L), dots)))
test(2253.12, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]), c(ja_ichi, rep(paste0(ja_ichi, dots), 3L)))
# Tests for combined characters, multiple columns
DT = data.table(paste0(ja_ichi), strrep(ja_ni, 2L), strrep(ja_ko, 3L), strrep(accented_a, 2L), "aaa")
test(2253.13, options=list(datatable.prettyprint.char = 4L), capture.output(print(DT))[-1L], paste("1:", ja_ichi, strrep(ja_ni, 2L), strrep(ja_ko, 3L), strrep(accented_a, 2L), "aaa"))
test(2253.14, options=list(datatable.prettyprint.char = 3L), capture.output(print(DT))[-1L], paste("1:", ja_ichi, strrep(ja_ni, 2L), strrep(ja_ko, 3L), strrep(accented_a, 2L), "aaa"))
test(2253.15, options=list(datatable.prettyprint.char = 2L), capture.output(print(DT))[-1L], paste("1:", ja_ichi, strrep(ja_ni, 2), paste0(strrep(ja_ko, 2), dots) , strrep(accented_a, 2), "aa..."))
test(2253.16, options=list(datatable.prettyprint.char = 1L), capture.output(print(DT))[-1L], paste("1:", ja_ichi, paste0(ja_ni, dots), paste0(ja_ko, dots), paste0(accented_a, dots), "a..."))
# Tests for multiple columns, multiple rows
DT = data.table(strrep(ja_ko, 1:3L), strrep(ja_n, 2:4L), strrep(accented_a, 3))
test(2253.17, options=list(datatable.prettyprint.char = 4L), gsub(clean_regex, "", capture.output(print(DT))[-1L]),
c(paste0(ja_ko, " ", strrep(ja_n, 2L), " ", strrep(accented_a, 3L)),
paste0(strrep(ja_ko, 2L), " ", strrep(ja_n, 3L), " ", strrep(accented_a, 3L)),
paste(strrep(ja_ko, 3L), strrep(ja_n, 4L), strrep(accented_a, 3L))))
test(2253.18, options=list(datatable.prettyprint.char = 3L), gsub(clean_regex, "", capture.output(print(DT))[-1L]),
c(paste0(ja_ko, " ", strrep(ja_n, 2L), " ", strrep(accented_a, 3L)),
paste0(strrep(ja_ko, 2L), " ", strrep(ja_n, 3L), " ", strrep(accented_a, 3L)),
paste(strrep(ja_ko, 3L), paste0(strrep(ja_n, 3L), dots), strrep(accented_a, 3L))))
test(2253.19, options=list(datatable.prettyprint.char = 1L), gsub(clean_regex, "", capture.output(print(DT))[-1L]),
c(paste0(ja_ko, " ", paste0(ja_n, dots), " ", paste0(accented_a, dots)),
paste0(c(ja_ko, ja_n, accented_a), dots, collapse=" "),
paste0(c(ja_ko, ja_n, accented_a), dots, collapse=" ")))
})

# allow 1-D matrix in j for consistency, #783
DT=data.table(a = rep(1:2, 3), b = 1:6)
Expand Down
Loading