Skip to content

Fix truncation of long column names in print.data.table() #7802

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

Open
venom1204 wants to merge 8 commits into
base: master
Choose a base branch
from
+25 −12
Open

Fix truncation of long column names in print.data.table() #7802

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
249fd7a
updaqted
venom1204 Jun 20, 2026
4200f70
Merge remote-tracking branch 'origin/master' into issue7797
venom1204 Jun 24, 2026
ab897c5
added tests
venom1204 Jun 24, 2026
30a00ef
lintr
venom1204 Jun 24, 2026
c4b3481
testb add
venom1204 Jun 24, 2026
52990f1
removed blank lines
venom1204 Jun 24, 2026
9873073
..
venom1204 Jun 24, 2026
3699adc
added test
venom1204 Jun 25, 2026
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
28 changes: 16 additions & 12 deletions R/print.data.table.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,12 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
catf("Null %s (0 rows and 0 cols)\n", x_class) # See FAQ 2.5 and NEWS item in v1.8.9
} else {
catf("Empty %s (%d rows and %d cols)", x_class, NROW(x), NCOL(x))
if (length(x)>0L) cat(": ",paste(head(names(x),6L),collapse=","),if(length(x)>6L)"...",sep="") # notranslate
if (length(x)>0L) {
# Minimal truncation for empty table summary line
e_trunc = getOption("datatable.prettyprint.char") %||% (getOption("width") - 5L)
t_names = char.trunc(head(names(x), 6L), trunc.char = e_trunc)
Comment on lines +63 to +64

@tdhock tdhock Jun 27, 2026

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.

can these 5L and 6L get put in variables with informative names so we can understand where they come from? or please at least add a comment to explain?

@venom1204 venom1204 Jun 27, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

just wanted to ask on thing that should `datatable.prettyprint.char = Inf`` also disable truncation of column names, or should column names always respect the available print width?

@venom1204 venom1204 Jun 27, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

this is what i got for the first twotests

> options(width=20)
print(data.table(abcdefghijklmnopqrstuvwxyz=1))
   abcdefghijklmn...
               <num>
1:                 1
> options(width=20,
        datatable.print.trunc.cols=TRUE,
        datatable.print.class=TRUE)
print(data.table(abcdefghijklmnopqrstuvwxyz=1))
1 variable not shown: [abcdefghijklmn... <num>]

cat(": ", paste(t_names, collapse=","), if(length(x)>6L)"...", sep="") # notranslate
}
cat("\n") # notranslate
}
return(invisible(x))
Expand All @@ -74,7 +79,6 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
}
n_x = nrow(x)
if ((topn*2L+1L)<n_x && (n_x>nrows || !topnmiss)) {
toprint = rbindlist(list(head(x, topn), tail(x, topn)), use.names=FALSE) # no need to match names because head and tail of same x, and #3306
rn = c(seq_len(topn), seq.int(to=n_x, length.out=topn))
printdots = TRUE
idx = c(seq_len(topn), seq(to=nrow(x), length.out=topn))
Expand All @@ -88,12 +92,12 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
}
require_bit64_if_needed(x)
classes = classes1(toprint)
trunc.char = getOption("datatable.prettyprint.char")
if (is.null(trunc.char)) {
rn_w = if (isTRUE(row.names)) nchar(as.character(max(rn))) + 2L else 0L
trunc.char = max(0L, getOption("width") - rn_w - 3L)
}

rn_w = if (isTRUE(row.names)) nchar(as.character(max(rn))) + 2L else 0L
width_limit = max(0L, getOption("width") - rn_w - 3L)
Comment on lines +96 to +97

@tdhock tdhock Jun 27, 2026

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.

same here please explain 0L 3L 2L?

trunc.char = getOption("datatable.prettyprint.char") %||% width_limit
toprint=format.data.table(toprint, na.encode=FALSE, timezone = timezone, trunc.char = trunc.char, ...) # na.encode=FALSE so that NA in character cols print as <NA>
if (col.names != "none") colnames(toprint) = char.trunc(colnames(toprint), trunc.char = width_limit)

# FR #353 - add row.names = logical argument to print.data.table
if (isTRUE(row.names)) rownames(toprint)=paste0(format(rn,right=TRUE,scientific=FALSE),":") else rownames(toprint)=rep.int("", nrow(toprint))
Expand Down Expand Up @@ -122,7 +126,7 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
cols_to_print = widths < cons_width
not_printed = colnames(toprint)[!cols_to_print]
if (!any(cols_to_print)) {
trunc_cols_message(not_printed, abbs, class, col.names)
trunc_cols_message(not_printed, abbs, class, col.names, trunc.char = width_limit)
return(invisible(x))
}
# When nrow(toprint) = 1, attributes get lost in the subset,
Expand All @@ -134,7 +138,7 @@ print.data.table = function(x, topn=getOption("datatable.print.topn"),
if (col.names != "none") cut_colnames = identity
cut_colnames(print(x, right=TRUE, quote=quote, na.print=na.print))
# prints names of variables not shown in the print
if (trunc.cols) trunc_cols_message(not_printed, abbs, class, col.names)
if (trunc.cols) trunc_cols_message(not_printed, abbs, class, col.names, trunc.char = width_limit)
}
if (printdots) {
if (isFALSE(row.names)) {
Expand Down Expand Up @@ -253,7 +257,7 @@ format_list_item.data.frame = function(x, ...) {
# Current implementation may have issues when dealing with strings that have combinations of full-width and half-width characters,
# if this becomes a problem in the future, we could consider string traversal instead.
char.trunc = function(x, trunc.char = getOption("datatable.prettyprint.char")) {
if (is.null(trunc.char)) return(x)
if (is.null(trunc.char) || is.infinite(trunc.char[1L])) return(x)
trunc.char = max(0L, suppressWarnings(as.integer(trunc.char[1L])), na.rm=TRUE)
if (!is.character(x) || trunc.char <= 0L) return(x)
nchar_width = nchar(x, 'width', allowNA = TRUE)
Expand Down Expand Up @@ -291,12 +295,12 @@ toprint_subset = function(x, cols_to_print) {
}
}
# message for when trunc.cols=TRUE and some columns are not printed
trunc_cols_message = function(not_printed, abbs, class, col.names){
trunc_cols_message = function(not_printed, abbs, class, col.names, trunc.char = getOption("datatable.prettyprint.char")){
n = length(not_printed)
if (class && col.names != "none") classes = paste0(" ", tail(abbs, n)) else classes = ""
catf(
ngettext(n, "%d variable not shown: %s\n", "%d variables not shown: %s\n"),
n, brackify(paste0(not_printed, classes)),
n, brackify(paste0(char.trunc(not_printed, trunc.char = trunc.char), classes)),
domain=NA
)
}
Expand Down
9 changes: 9 additions & 0 deletions inst/tests/tests.Rraw
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21683,3 +21683,12 @@ max_ppsize = local({
x = as.data.table(as.list(1:max_ppsize))
test(2376, rbindlist(list(x)), x)
rm(x, max_ppsize)

#7797 long column names go past width
test(2377.1, print(data.table(abcdefghijklmnopqrstuvwxyz=1)), output="abcdefghijklmn...", options=list(width=20))
test(2377.2, print(data.table(abcdefghijklmnopqrstuvwxyz=1)), output="1 variable not shown: \\[abcdefghijklmn... <num>\\]", options=list(width=20, datatable.print.trunc.cols=TRUE, datatable.print.class=TRUE))

@tdhock tdhock Jun 25, 2026

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.

please add a test with more than one column.

  • 3 cols: two too long, one not
  • 4 cols: one too long, next not, next too long, next not
  • etc

@venom1204 venom1204 Jun 25, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

i added two tests , are they satisfying what you were excpecting.
thanks.

@tdhock tdhock Jun 27, 2026

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.

this is better but the test output has regex so difficult for me to see what it actually prints as, can you please add the output of these tests in a PR comment?

test(2377.3, print(data.table(abcdefghijklmnopqrst=1)), output="abcdefghijklmnopqrst", options=list(width=30))
test(2377.4, print(data.table(abcdefghijklmnopqrstuvwxyz=1, zyxwvutsrqponmlkjihgfedcba=2)), output="zyxwvutsrqponm...", options=list(width=40, datatable.print.trunc.cols=TRUE))

@joshhwuu joshhwuu Jun 26, 2026

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.

it looks like we're only asserting the footer output here? can we make the assertions stronger?

test(2377.5, print(data.table(abcdefghijklmnopqrstuvwxyz=1)), output="1 variable not shown: \\[abcdefghijklmn... <num>\\]", options=list(width=20, datatable.print.trunc.cols=TRUE, datatable.print.class=TRUE, datatable.prettyprint.char=Inf))
test(2377.6, print(data.table(very_long_name_a=1, s_b=2, very_long_name_c=3)), output="very_long_name_a[ ]+s_b.*1 variable not shown: \\[very_long_name_c <num>\\]", options=list(width=35, datatable.print.trunc.cols=TRUE, datatable.print.class=TRUE))
test(2377.7, print(data.table(extremely_long_a=1, s_b=2, extremely_long_c=3, s_d=4)), output="extremely_long_a[ ]+s_b.*2 variables not shown: \\[extremely_long_c <num>, s_d <num>\\]", options=list(width=30, datatable.print.trunc.cols=TRUE, datatable.print.class=TRUE))
Loading