Merge branch 'master' into issue6846

Rdatatable · Mar 4, 2025 · a0b7f2b · a0b7f2b
2 parents 58dff19 + 5c964b3
commit a0b7f2b
Show file tree

Hide file tree

Showing 34 changed files with 132 additions and 48 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -15,9 +15,9 @@ Authors@R: c(
   person("Tyson","Barrett",        role=c("aut","cre"), email="t.barrett88@gmail.com", comment = c(ORCID="0000-0002-2137-1391")),
   person("Matt","Dowle",           role="aut",          email="mattjdowle@gmail.com"),
   person("Arun","Srinivasan",      role="aut",          email="asrini@pm.me"),
-  person("Jan","Gorecki",          role="aut"),
-  person("Michael","Chirico",      role="aut", comment = c(ORCID="0000-0003-0787-087X")),
-  person("Toby","Hocking",         role="aut", comment = c(ORCID="0000-0002-3146-0865")),
+  person("Jan","Gorecki",          role="aut",          email="j.gorecki@wit.edu.pl"),
+  person("Michael","Chirico",      role="aut",          email="michaelchirico4@gmail.com", comment = c(ORCID="0000-0003-0787-087X")),
+  person("Toby","Hocking",         role="aut",          email="toby.hocking@r-project.org", comment = c(ORCID="0000-0002-3146-0865")),
   person("Benjamin","Schwendinger",role="aut", comment = c(ORCID="0000-0003-3315-8114")),
   person("Ivan", "Krylov",         role="aut",          email="ikrylov@disroot.org",   comment = c(ORCID="0000-0002-0172-3812")),
   person("Pasha","Stetsenko",      role="ctb"),

diff --git a/src/data.table.h b/src/data.table.h
@@ -17,6 +17,10 @@
 #if R_VERSION < R_Version(3, 4, 0)
 #  define SET_GROWABLE_BIT(x)  // #3292
 #endif
+// TODO: remove the `R_SVN_VERSION` check when R 4.5.0 is released (circa Apr. 2025)
+#if R_VERSION < R_Version(4, 5, 0) || R_SVN_REVISION < 86702
+#  define isDataFrame(x) isFrame(x) // #6180
+#endif
 #include <Rinternals.h>
 #define SEXPPTR_RO(x) ((const SEXP *)DATAPTR_RO(x))  // to avoid overhead of looped STRING_ELT and VECTOR_ELT
 #include <stdint.h>    // for uint64_t rather than unsigned long long

diff --git a/src/dogroups.c b/src/dogroups.c
@@ -283,7 +283,7 @@ SEXP dogroups(SEXP dt, SEXP dtcols, SEXP groups, SEXP grpcols, SEXP jiscols, SEX
       for (int j=0; j<LENGTH(jval); ++j) {
         thiscol = VECTOR_ELT(jval,j);
         if (isNull(thiscol)) continue;
-        if (!isVector(thiscol) || isFrame(thiscol))
+        if (!isVector(thiscol) || isDataFrame(thiscol))
           error(_("Entry %d for group %d in j=list(...) should be atomic vector or list. If you are trying something like j=list(.SD,newcol=mean(colA)) then use := by group instead (much quicker), or cbind or merge afterwards."), j+1, i+1);
         if (isArray(thiscol)) {
           SEXP dims = PROTECT(getAttrib(thiscol, R_DimSymbol));

diff --git a/src/forder.c b/src/forder.c
@@ -1616,7 +1616,7 @@ void putIndex(SEXP x, SEXP cols, SEXP o) {
 
 // isTRUE(getOption("datatable.use.index"))
 bool GetUseIndex(void) {
-  SEXP opt = GetOption(install("datatable.use.index"), R_NilValue);
+  SEXP opt = GetOption1(install("datatable.use.index"));
   if (!IS_TRUE_OR_FALSE(opt))
     error(_("'datatable.use.index' option must be TRUE or FALSE")); // # nocov
   return LOGICAL(opt)[0];
@@ -1627,7 +1627,7 @@ bool GetAutoIndex(void) {
   // for now temporarily 'forder.auto.index' not 'auto.index' to disabled it by default
   // because it writes attr on .SD which is re-used by all groups leading to incorrect results
   // DT[, .(uN=uniqueN(.SD)), by=A]
-  SEXP opt = GetOption(install("datatable.forder.auto.index"), R_NilValue);
+  SEXP opt = GetOption1(install("datatable.forder.auto.index"));
   if (isNull(opt))
     return false;
   if (!IS_TRUE_OR_FALSE(opt))

diff --git a/src/fread.c b/src/fread.c
@@ -1730,8 +1730,10 @@ int freadMain(freadMainArgs _args) {
             topQuoteRule = quoteRule;
             firstJumpEnd = ch;  // to know how many bytes jump 0 is, for nrow estimate later (a less-good estimate when fill=true since line lengths vary more)
             if (verbose) {
-              DTPRINT((unsigned)sep<32 ? "  sep=%#02x" : "  sep='%c'", sep); // # notranslate
-              DTPRINT(_("  with %d fields using quote rule %d\n"), topNumFields, quoteRule);
+                DTPRINT((unsigned)sep<32
+                        ? _("  sep=%#02x  with %d fields using quote rule %d\n")
+                        : _("  sep='%c'  with %d fields using quote rule %d\n"),
+                        sep, topNumFields, quoteRule);
             }
           }
         } else {
@@ -1780,8 +1782,10 @@ int freadMain(freadMainArgs _args) {
             topSkip = thisRow-thisBlockLines;
             if (topSkip<0) topSkip=0;       // inelegant but will do for now to pass single row input such as test 890
             if (verbose) {
-              DTPRINT((unsigned)sep<32 ? "  sep=%#02x" : "  sep='%c'", sep); // # notranslate
-              DTPRINT(_("  with %d lines of %d fields using quote rule %d\n"), topNumLines, topNumFields, topQuoteRule);
+                DTPRINT((unsigned)sep<32
+                        ? _("  sep=%#02x  with %d lines of %d fields using quote rule %d\n")
+                        : _("  sep='%c'  with %d lines of %d fields using quote rule %d\n"),
+                        sep, topNumLines, topNumFields, topQuoteRule);
             }
           }
         }

diff --git a/src/freadR.c b/src/freadR.c
@@ -132,7 +132,7 @@ SEXP freadR(
   args.logical01 = LOGICAL(logical01Arg)[0];
   args.logicalYN = LOGICAL(logicalYNArg)[0];
   {
-    SEXP tt = PROTECT(GetOption(sym_old_fread_datetime_character, R_NilValue));
+    SEXP tt = PROTECT(GetOption1(sym_old_fread_datetime_character));
     args.oldNoDateTime = oldNoDateTime = isLogical(tt) && LENGTH(tt)==1 && LOGICAL(tt)[0]==TRUE;
     UNPROTECT(1);
   }

diff --git a/src/init.c b/src/init.c
@@ -329,7 +329,7 @@ inline double LLtoD(long long x) {
 
 int GetVerbose(void) {
   // don't call repetitively; save first in that case
-  SEXP opt = GetOption(sym_verbose, R_NilValue);
+  SEXP opt = GetOption1(sym_verbose);
   if ((!isLogical(opt) && !isInteger(opt)) || LENGTH(opt)!=1 || INTEGER(opt)[0]==NA_INTEGER)
     error(_("verbose option must be length 1 non-NA logical or integer"));
   return INTEGER(opt)[0];

diff --git a/src/rbindlist.c b/src/rbindlist.c
@@ -228,7 +228,7 @@ SEXP rbindlist(SEXP l, SEXP usenamesArg, SEXP fillArg, SEXP idcolArg, SEXP ignor
         }
       }
       if (buff[0]) {
-        SEXP opt = GetOption(install("datatable.rbindlist.check"), R_NilValue);
+        SEXP opt = GetOption1(install("datatable.rbindlist.check"));
         if (!isNull(opt) && !(isString(opt) && length(opt)==1)) {
           warning(_("options()$datatable.rbindlist.check is set but is not a single string. See news item 5 in v1.12.2."));
           opt = R_NilValue;

diff --git a/src/subset.c b/src/subset.c
@@ -296,7 +296,7 @@ SEXP subsetDT(SEXP x, SEXP rows, SEXP cols) { // API change needs update NEWS.md
     if (this<1 || this>LENGTH(x)) error(_("Item %d of cols is %d which is outside the range [1,ncol(x)=%d]"), i+1, this, LENGTH(x));
   }
 
-  int overAlloc = checkOverAlloc(GetOption(install("datatable.alloccol"), R_NilValue));
+  int overAlloc = checkOverAlloc(GetOption1(install("datatable.alloccol")));
   SEXP ans = PROTECT(allocVector(VECSXP, LENGTH(cols)+overAlloc)); nprotect++;  // doing alloc.col directly here; eventually alloc.col can be deprecated.
 
   // user-defined and superclass attributes get copied as from v1.12.0

diff --git a/vignettes/_translation_links.R b/vignettes/_translation_links.R
@@ -0,0 +1,23 @@
+# build a link list of alternative languages (may be character(0))
+# idea is to look like 'Other languages: en | fr | de'
+.write.translation.links <- function(fmt) {
+    url = "https://rdatatable.gitlab.io/data.table/articles"
+    path = dirname(knitr::current_input(TRUE))
+    if (basename(path) == "vignettes") {
+      lang = "en"
+    } else {
+      lang = basename(path)
+      path = dirname(path)
+    }
+    translation = dir(path,
+      recursive = TRUE,
+      pattern = glob2rx(knitr::current_input(FALSE))
+    )
+    transl_lang = ifelse(dirname(translation) == ".", "en", dirname(translation))
+    block = if (!all(transl_lang == lang)) {
+      linked_transl = sprintf("[%s](%s)", transl_lang, file.path(url, sub("(?i)\\.Rmd$", ".html", translation)))
+      linked_transl[transl_lang == lang] = lang
+      sprintf(fmt, paste(linked_transl, collapse = " | "))
+    } else ""
+    knitr::asis_output(block)
+}
diff --git a/vignettes/datatable-benchmarking.Rmd b/vignettes/datatable-benchmarking.Rmd
@@ -25,9 +25,9 @@ h2 {
 }
 </style>
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-benchmarking.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 This document is meant to guide on measuring performance of `data.table`. Single place to document best practices and traps to avoid.
 

diff --git a/vignettes/datatable-faq.Rmd b/vignettes/datatable-faq.Rmd
@@ -26,9 +26,9 @@ h2 {
 }
 </style>
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-faq.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 library(data.table)

diff --git a/vignettes/datatable-importing.Rmd b/vignettes/datatable-importing.Rmd
@@ -15,10 +15,9 @@ h2 {
 }
 </style>
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-importing.html)
-* [Russian](https://rdatatable.gitlab.io/data.table/articles/ru/datatable-importing.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 This document is focused on using `data.table` as a dependency in other R packages. If you are interested in using `data.table` C code from a non-R application, or in calling its C functions directly, jump to the [last section](#non-r-api) of this vignette.
 

diff --git a/vignettes/datatable-intro.Rmd b/vignettes/datatable-intro.Rmd
@@ -9,10 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-intro.html)
-* [Russian](https://rdatatable.gitlab.io/data.table/articles/ru/datatable-intro.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)

diff --git a/vignettes/datatable-joins.Rmd b/vignettes/datatable-joins.Rmd
@@ -22,6 +22,10 @@ knitr::opts_chunk$set(
 )
 ```
 
+```{r, echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 In this vignette you will learn how to perform any join operation using resources available in the `data.table` syntax.
 
 It assumes familiarity with the `data.table` syntax. If that is not the case, please read the following vignettes:

diff --git a/vignettes/datatable-keys-fast-subset.Rmd b/vignettes/datatable-keys-fast-subset.Rmd
@@ -9,9 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-keys-fast-subset.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)

diff --git a/vignettes/datatable-programming.Rmd b/vignettes/datatable-programming.Rmd
@@ -9,9 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-programming.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r init, include = FALSE}
 require(data.table)
@@ -24,7 +24,6 @@ knitr::opts_chunk$set(
 )
 ```
 
-
 ## Introduction
 
 `data.table`, from its very first releases, enabled the usage of `subset` and `with` (or `within`) functions by defining the `[.data.table` method. `subset` and `with` are base R functions that are useful for reducing repetition in code, enhancing readability, and reducing number the total characters the user has to type. This functionality is possible in R because of a quite unique feature called *lazy evaluation*. This feature allows a function to catch its arguments, before they are evaluated, and to evaluate them in a different scope than the one in which they were called. Let's recap usage of the `subset` function.

diff --git a/vignettes/datatable-reference-semantics.Rmd b/vignettes/datatable-reference-semantics.Rmd
@@ -9,9 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-reference-semantics.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
@@ -23,6 +23,7 @@ knitr::opts_chunk$set(
  collapse = TRUE)
 .old.th = setDTthreads(1)
 ```
+
 This vignette discusses *data.table*'s reference semantics which allows to *add/update/delete* columns of a *data.table by reference*, and also combine them with `i` and `by`. It is aimed at those who are already familiar with *data.table* syntax, its general form, how to subset rows in `i`, select and compute on columns, and perform aggregations by group. If you're not familiar with these concepts, please read the [`vignette("datatable-intro", package="data.table")`](datatable-intro.html) vignette first.
 
 ***

diff --git a/vignettes/datatable-reshape.Rmd b/vignettes/datatable-reshape.Rmd
@@ -9,10 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-reshape.html)
-* [Russian](https://rdatatable.gitlab.io/data.table/articles/ru/datatable-reshape.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)

diff --git a/vignettes/datatable-sd-usage.Rmd b/vignettes/datatable-sd-usage.Rmd
@@ -21,9 +21,9 @@ vignette: >
 }
 </style>
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-sd-usage.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)

diff --git a/vignettes/datatable-secondary-indices-and-auto-indexing.Rmd b/vignettes/datatable-secondary-indices-and-auto-indexing.Rmd
@@ -9,9 +9,9 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
-Translations of this document are available in
-
-* [French](https://rdatatable.gitlab.io/data.table/articles/fr/datatable-secondary-indices-and-auto-indexing.html)
+```{r echo=FALSE, file='_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
 
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)

diff --git a/vignettes/fr/datatable-benchmarking.Rmd b/vignettes/fr/datatable-benchmarking.Rmd
@@ -18,6 +18,10 @@ h2 {
 }
 </style>
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 Ce document a pour but de guider la mesure de la performance de `data.table`. Il centralise la documentation des meilleures pratiques et des pièges à éviter.
 
 # fread : effacer les caches

diff --git a/vignettes/fr/datatable-faq.Rmd b/vignettes/fr/datatable-faq.Rmd
@@ -19,6 +19,10 @@ h2 {
 #TOC { width: 100%; }
 </style>
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 library(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-importing.Rmd b/vignettes/fr/datatable-importing.Rmd
@@ -15,6 +15,10 @@ h2 {
 }
 </style>
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 Ce document se concentre sur l'utilisation de `data.table` comme dépendance dans d'autres packages R. Si vous souhaitez utiliser le code C de `data.table` à partir d'une application non-R, ou appeler directement ses fonctions C, passez à la [dernière section](#non-r-API) de cette vignette.
 
 Importer `data.table` n'est pas différent qu'importer d'autres packages R. Cette vignette a pour but de répondre aux questions les plus courantes à ce sujet; les indications présentées ici peuvent être appliquées à d'autres packages R.

diff --git a/vignettes/fr/datatable-intro.Rmd b/vignettes/fr/datatable-intro.Rmd
@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-keys-fast-subset.Rmd b/vignettes/fr/datatable-keys-fast-subset.Rmd
@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-programming.Rmd b/vignettes/fr/datatable-programming.Rmd
@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r init, include = FALSE}
 require(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-reference-semantics.Rmd b/vignettes/fr/datatable-reference-semantics.Rmd
@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-reshape.Rmd b/vignettes/fr/datatable-reshape.Rmd
@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
 knitr::opts_chunk$set(

diff --git a/vignettes/fr/datatable-sd-usage.Rmd b/vignettes/fr/datatable-sd-usage.Rmd
@@ -12,6 +12,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r echo=FALSE, file='../_translation_links.R'}
+```
+`r .write.translation.links("Translations of this document are available in: %s")`
+
 ```{r, echo = FALSE, message = FALSE}
 require(data.table)
 knitr::opts_chunk$set(