Merge branch 'master' into autoprint-subclass

.gitlab-ci.yml

@@ -194,6 +194,7 @@ test-lin-dev-clang-cran:
     - echo 'CFLAGS=-g -O2 -fno-common -Wall -Wvla -pedantic -fstack-protector-strong -D_FORTIFY_SOURCE=2' > ~/.R/Makevars
     - echo 'CXXFLAGS=-g -O2 -fno-common -Wall -Wvla -pedantic -fstack-protector-strong -D_FORTIFY_SOURCE=2' >> ~/.R/Makevars
     - *install-deps
+    - clang-tidy -extra-arg=-I/usr/local/lib/R/include -checks='readability-inconsistent-declaration-parameter' src/*.c -- -std=c99
     - R CMD check --as-cran $(ls -1t data.table_*.tar.gz | head -n 1)
     - (! grep "warning:" data.table.Rcheck/00install.out)
     - >-

DESCRIPTION

@@ -99,5 +99,6 @@ Authors@R: c(
   person("Elise", "Maigné",        role="ctb"),
   person("Vincent", "Rocher",      role="ctb"),
   person("Vijay", "Lulla",         role="ctb"),
-  person("Aljaž", "Sluga",         role="ctb")
+  person("Aljaž", "Sluga",         role="ctb"),
+  person("Bill", "Evans",          role="ctb")
   )

NAMESPACE

@@ -202,6 +202,7 @@ S3method(format_col, POSIXct)
 S3method(format_col, expression)
 export(format_list_item)
 S3method(format_list_item, default)
+S3method(format_list_item, data.frame)
 
 export(fdroplevels, setdroplevels)
 S3method(droplevels, data.table)

NEWS.md

@@ -113,6 +113,10 @@ rowwiseDT(
 
 13. `rbindlist(l, use.names=TRUE)` can now handle different encodings for the column names in different entries of `l`, [#5452](https://github.com/Rdatatable/data.table/issues/5452). Thanks to @MEO265 for the report, and Benjamin Schwendinger for the fix.
 
+14. Added a `data.frame` method for `format_list_item()` to fix error printing data.tables with columns containing 1-column data.frames, [#6592](https://github.com/Rdatatable/data.table/issues/6592). Thanks to @r2evans for the bug report and fix.
+
+15. The auto-printing suppression in `knitr` documents is now done by implementing a method for `knit_print` instead of looking up the call stack, [#6589](https://github.com/Rdatatable/data.table/pull/6589). Thanks to @jangorecki for the report [#6509](https://github.com/Rdatatable/data.table/issues/6509) and @aitap for the fix.
+
 ## NOTES
 
 1. Tests run again when some Suggests packages are missing, [#6411](https://github.com/Rdatatable/data.table/issues/6411). Thanks @aadler for the note and @MichaelChirico for the fix.

R/onLoad.R

@@ -66,15 +66,14 @@
       lockBinding("rbind.data.frame",baseenv())
     }
   }
-  if (session_r_version < "3.6.0") {
+  if (session_r_version < "3.6.0") { # corresponds to S3method() directive in NAMESPACE
     # no delayed registration support for NAMESPACE; perform it manually
     if (isNamespaceLoaded("knitr")) {
       registerS3method("knit_print", "data.table", knit_print.data.table, envir = asNamespace("knitr"))
-    } else {
-      setHook(packageEvent("knitr", "onLoad"), function(...) {
-        registerS3method("knit_print", "data.table", knit_print.data.table, envir = asNamespace("knitr"))
-      })
     }
+    setHook(packageEvent("knitr", "onLoad"), function(...) {
+      registerS3method("knit_print", "data.table", knit_print.data.table, envir = asNamespace("knitr"))
+    })
   }
 
   # Set options for the speed boost in v1.8.0 by avoiding 'default' arg of getOption(,default=)

R/print.data.table.R

@@ -231,6 +231,11 @@ format_list_item.default = function(x, ...) {
   }
 }
 
+# #6592 -- nested 1-column frames breaks printing
+format_list_item.data.frame = function(x, ...) {
+  paste0("<", class1(x), paste_dims(x), ">")
+}
+
 # FR #1091 for pretty printing of character
 # TODO: maybe instead of doing "this is...", we could do "this ... test"?
 # Current implementation may have issues when dealing with strings that have combinations of full-width and half-width characters,

inst/tests/tests.Rraw

@@ -20651,3 +20651,16 @@ test(2298.2, rbindlist(list(y,x), use.names=TRUE), data.table("\u00f6"=c(4,2), "
 set(y, j="\u00e4", value=NULL)
 test(2298.3, rbindlist(list(x,y), use.names=TRUE, fill=TRUE), data.table("\u00e4"=c(1,NA), "\u00f6"=c(2,4), "\u00fc"=c(3,5)))
 test(2298.4, rbindlist(list(y,x), use.names=TRUE, fill=TRUE), data.table("\u00f6"=c(4,2),  "\u00fc"=c(5,3), "\u00e4"=c(NA,1)))
+
+# #6592: printing nested single-column frames
+test(2299.01, format_list_item(data.frame(a=1)),                      output="<data.frame[1x1]>")
+test(2299.02, format_list_item(data.frame(a=1)[0,,drop=FALSE]),       output="<data.frame[0x1]>")
+test(2299.03, format_list_item(data.frame(a=1)[,0]),                  output="<data.frame[1x0]>")
+test(2299.04, format_list_item(data.frame(a=1, b=2)[0,,drop=FALSE]),  output="<data.frame[0x2]>")
+test(2299.06, format_list_item(data.table(a=1)),                      output="<data.table[1x1]>")
+test(2299.07, format_list_item(data.table(a=numeric())),              output="<data.table[0x1]>")
+test(2299.08, format_list_item(data.table()),                         output="<data.table[0x0]>")
+test(2299.09, format_list_item(data.table(a=numeric(), b=numeric())), output="<data.table[0x2]>")
+test(2299.10, data.table(a=1),                                        output="a\n1: *1")
+test(2299.11, data.table(a=list(data.frame(b=1))),                    output="a\n1: <data.frame[1x1]>")
+test(2299.12, data.table(a=list(data.table(b=1))),                    output="a\n1: <data.table[1x1]>")

tests/autoprint.R

@@ -44,6 +44,18 @@ tryCatch(DT[,foo:=ColumnNameTypo], error=function(e) e$message)         # error:
 DT                                    # yes
 DT                                    # yes
 
+# Regression test for auto-printing suppression in source(), #2369
+local({
+  f = tempfile(fileext = ".R")
+  on.exit(unlink(f))
+  writeLines(c(
+    "library(data.table)",
+    "DT = data.table(a = 1)",
+    "DT[,a:=1]"                       # no
+  ), f)
+  source(f, local = TRUE, echo = TRUE)
+})
+
 # child class of data.table doesn't induce unintended print, #3029
 dt <- data.table(x = 1)
 class(dt) <- c("foo", "data.table", "data.frame")

tests/autoprint.Rout.save

@@ -152,6 +152,23 @@ NULL
 1:    10
 2:    10
 > 
+> # Regression test for auto-printing suppression in source(), #2369
+> local({
++   f = tempfile(fileext = ".R")
++   on.exit(unlink(f))
++   writeLines(c(
++     "library(data.table)",
++     "DT = data.table(a = 1)",
++     "DT[,a:=1]"                       # no
++   ), f)
++   source(f, local = TRUE, echo = TRUE)
++ })
+
+> library(data.table)
+
+> DT = data.table(a = 1)
+
+> DT[, `:=`(a, 1)]
 > # child class of data.table doesn't induce unintended print, #3029
 > dt <- data.table(x = 1)
 > class(dt) <- c("foo", "data.table", "data.frame")

vignettes/datatable-intro.Rmd

@@ -643,6 +643,26 @@ DT[, print(list(c(a,b))), by = ID] # (2)
 
 In (1), for each group, a vector is returned, with length = 6,4,2 here. However, (2) returns a list of length 1 for each group, with its first element holding vectors of length 6,4,2. Therefore, (1) results in a length of ` 6+4+2 = `r 6+4+2``, whereas (2) returns `1+1+1=`r 1+1+1``.
 
+Flexibility of j allows us to store any list object as an element of data.table.  For example, when statistical models are fit to groups, these models can be stored in a data.table.  Code is concise and easy to understand.
+
+```{r}
+## Do long distance flights cover up departure delay more than short distance flights?
+## Does cover up vary by month?
+flights[, `:=`(makeup = dep_delay - arr_delay)]
+
+makeup.models <- flights[, .(fit = list(lm(makeup ~ distance))), by = .(month)]
+makeup.models[, .(coefdist = coef(fit[[1]])[2], rsq = summary(fit[[1]])$r.squared), by = .(month)]
+```
+Using data.frames, we need more complicated code to obtain same result.
+```{r}
+setDF(flights)
+flights.split <- split(flights, f = flights$month)
+makeup.models.list <- lapply(flights.split, function(df) c(month = df$month[1], fit = list(lm(makeup ~ distance, data = df))))
+makeup.models.df <- do.call(rbind, makeup.models.list)
+sapply(makeup.models.df[, "fit"], function(model) c(coefdist = coef(model)[2], rsq =  summary(model)$r.squared)) |> t() |> data.frame()
+setDT(flights)
+```
+
 ## Summary
 
 The general form of `data.table` syntax is: