annotate truncated entries with their length (#7129)

Co-authored-by: Benjamin Schwendinger <[email protected]>

Author: MichaelChirico

NEWS.md

@@ -101,6 +101,7 @@
    + On non-Windows systems, `fread()` now prints the reason why the file couldn't be opened, which could also be due to it being too large to map.
    + With `verbose=TRUE`, file sizes are now printed using correct binary SI prefixes (the sizes have always been reported as bytes denominated in powers of `2^10`, so e.g. `1024*1024` bytes was reported as `1 MB` where `1 MiB` or `1.05 MB` is correct).
 
+4. The default `format_list_item()` method (and hence `print.data.table()`) annotates truncated list items with their length, [#605](https://github.com/Rdatatable/data.table/issues/605). Thanks Matt Dowle for the original report (2012!) and @MichaelChirico for the fix.
 
 # data.table [v1.17.8](https://github.com/Rdatatable/data.table/milestone/41) (6 July 2025)
 

R/print.data.table.R

@@ -227,7 +227,7 @@ format_list_item.default = function(x, ...) {
   if (is.null(x))  # NULL item in a list column
     "[NULL]" # not '' or 'NULL' to distinguish from those "common" string values in data
   else if (is.atomic(x) || inherits(x, "formula")) # FR #2591 - format.data.table issue with columns of class "formula"
-    paste(c(format(head(x, 6L), ...), if (length(x) > 6L) "..."), collapse=",") # fix for #5435 and #37 - format has to be added here...
+    paste(c(format(head(x, 6L), ...), if (length(x) > 6L) sprintf("...[%d]", length(x))), collapse=",") # fix for #5435, #37, and #605 - format has to be added here...
   else if (has_format_method(x) && length(formatted<-format(x, ...))==1L) {
     # the column's class does not have a format method (otherwise it would have been used by format_col and this
     # format_list_item would not be reached) but this particular list item does have a format method so use it

inst/tests/tests.Rraw

@@ -349,7 +349,7 @@ xenv = new.env()   # to control testing tables()
 xenv$DT = data.table(a = 1)
 test(69.5, nrow(tables(env=xenv)), 1L, output="NAME NROW NCOL MB COLS    KEY\n1:   DT    1    1  0    a [NULL]\nTotal: 0MB")
 xenv$DT = data.table(A=1:2, B=3:4, C=5:6, D=7:8, E=9:10, F=11:12, G=13:14, H=15:16, key=c("A", "D", "F", "G"))
-test(69.6, nrow(tables(env=xenv)), 1L, output="NAME NROW NCOL MB            COLS     KEY\n1:   DT    2    8  0 A,B,C,D,E,F,... A,D,F,G.*Total: 0MB")
+test(69.6, nrow(tables(env=xenv)), 1L, output="NAME NROW NCOL MB\\s+COLS\\s+KEY\n1:   DT    2    8  0 A,B,C,D,E,F,\\.\\.\\.\\[8\\] A,D,F,G.*Total: 0MB")
 rm(xenv)
 test(69.7, tables(order.col='asdf'), error="not a column name of info")
 
@@ -1732,8 +1732,8 @@ test(557, DT[, f(.SD), by=x], error="[.]SD is locked.*reserved for possible futu
 
 # Test printing on nested data.table, bug #1803
 DT = data.table(x=letters[1:3], y=list(1:10, letters[1:4], data.table(a=1:3,b=4:6)))
-test(558, capture.output(print(DT)),
-     c("   x                 y", "1: a   1,2,3,4,5,6,...", "2: b           a,b,c,d", "3: c <data.table[3x2]>"))
+test(558.1, DT, output="\\ba\\s+1,2,3,4,5,6,\\.\\.\\.\\[10\\]") # row 1
+test(558.2, DT, output="\\bc\\s+<data\\.table\\[3x2\\]>")       # row 3
 test(559, setkey(DT,x)["a",y][[1]], 1:10)   # y is symbol representing list column, specially detected in dogroups
 
 # Test renaming of .N to N