Merge branch 'master' into master

AntonNM · web-flow · commit e5bb0e3af348 · 2025-02-03T13:27:09.000-05:00
diff --git a/.ci/linters/c/cocci_linter.R b/.ci/linters/c/cocci_linter.R
@@ -0,0 +1,20 @@
+cocci_linter = if (!nzchar(Sys.which("spatch"))) function(...) {} else function(c_obj) {
+  bad <- FALSE
+  for (spfile in list.files(".ci/linters/cocci", full.names = TRUE)) {
+    # Coccinelle parser gets confused sometimes, so ignore stderr and the exit code
+    out = suppressWarnings(system2(
+      "spatch",
+      shQuote(c(
+        "--sp-file", spfile, c_obj$path, "--recursive-includes",
+        "-I", R.home("include"), "-I", "src"
+      )),
+      stdout = TRUE, stderr = FALSE
+    ))
+    if (length(out) > 0) {
+      cat(sprintf("In file '%s', Coccinelle patch '%s' recommends the following changes:\n", c_obj$path, spfile))
+      writeLines(out)
+      bad <- TRUE
+    }
+  }
+  if (bad) stop("Please apply the changes above or fix the linter")
+}
diff --git a/.ci/linters/cocci/redundant_cast_to_same_pointer_type.cocci b/.ci/linters/cocci/redundant_cast_to_same_pointer_type.cocci
@@ -0,0 +1,6 @@
+@@
+type T;
+T* E;
+@@
+- (T*)
+  E
diff --git a/.ci/linters/md/heading_id_linter.R b/.ci/linters/md/heading_id_linter.R
@@ -0,0 +1,26 @@
+any_mismatch = FALSE
+
+# ensure that ids are limited to alphanumerics and dashes
+# (in particular, dots and underscores break the links)
+check_header_ids = function(md) {
+  # A bit surprisingly, some headings don't start with a letter.
+  # We're interested in those that set an id to link to, i.e., end with {#id}.
+  heading_captures = regmatches(md, regexec("^#+ \\S.*[{]#([^}]*)[}]$", md))
+  lines_with_id = which(lengths(heading_captures) > 0)
+  ids = vapply(heading_captures[lines_with_id], `[`, '', 2)
+  # ids must start with a letter and consist of alphanumerics or dashes.
+  good_ids = grepl('^[A-Za-z][A-Za-z0-9-]*$', ids)
+  for (line in lines_with_id[!good_ids]) cat(sprintf(
+    "On line %d, bad heading id '%s':\n%s\n",
+    line, heading_captures[[line]][2], heading_captures[[line]][1]
+  ))
+  !all(good_ids)
+}
+
+any_error = FALSE
+for (vignette in list.files('vignettes', pattern = "[.]Rmd$", recursive = TRUE, full.name = TRUE)) {
+  cat(sprintf("Checking vignette file %s...\n", vignette))
+  rmd_lines = readLines(vignette)
+  any_error = check_header_ids(rmd_lines) || any_error
+}
+if (any_error) stop("Please fix the vignette issues above.")
diff --git a/.github/workflows/code-quality.yaml b/.github/workflows/code-quality.yaml
@@ -35,6 +35,9 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: r-lib/actions/setup-r@v2
+      - name: Install Coccinelle
+        # relying on the action above us to have updated the package cache
+        run: /usr/bin/sudo apt-get -y install coccinelle
       - name: Lint
         run: |
           linter_env = new.env()
diff --git a/inst/po/ru/LC_MESSAGES/R-data.table.mo b/inst/po/ru/LC_MESSAGES/R-data.table.mo
diff --git a/inst/po/ru/LC_MESSAGES/data.table.mo b/inst/po/ru/LC_MESSAGES/data.table.mo
diff --git a/po/R-ru.po b/po/R-ru.po
@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: data.table 1.15.99\n"
 "POT-Creation-Date: 2025-01-29 23:31-0800\n"
-"PO-Revision-Date: 2025-01-31 13:52+0300\n"
+"PO-Revision-Date: 2025-02-02 22:32+0300\n"
 "Last-Translator: Ivan Krylov <ikrylov@disroot.org>\n"
 "Language-Team: Russian <https://translate.codeberg.org/projects/data-table-"
 "ru/gettext-R/ru/>\n"
@@ -3552,13 +3552,11 @@ msgstr[1] "%d переменные не показаны: %s\n"
 msgstr[2] "%d переменных не показано: %s\n"
 
 #: setops.R:46
-#, fuzzy
-#| msgid "unsupported column type(s) found in x or y: %s"
 msgid "unsupported column type found in x or y: %s"
 msgid_plural "unsupported column types found in x or y: %s"
-msgstr[0] "В «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
-msgstr[1] "В «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
-msgstr[2] "В «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
+msgstr[0] "в «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
+msgstr[1] "в «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
+msgstr[2] "в «x» или «y» нашлись столбцы неподдерживаемых типов: %s"
 
 #: test.data.table.R:255
 msgid "%d error out of %d. Search %s for test number %s. Duration: %s."
@@ -3569,10 +3567,6 @@ msgstr[1] "%d ошибки из %d. Ищите в %s тесты №№%s. Про
 msgstr[2] "%d ошибок из %d. Ищите в %s тесты №№%s. Продолжительность: %s."
 
 #: utils.R:36
-#, fuzzy
-#| msgid ""
-#| "%s has some duplicated column name(s): %s. Please remove or rename the "
-#| "duplicate(s) and try again."
 msgid ""
 "%s has duplicated column name %s. Please remove or rename the duplicate and "
 "try again."
diff --git a/po/data.table.pot b/po/data.table.pot
@@ -2692,12 +2692,12 @@ msgstr ""
 
 #: fwrite.c:909
 #, c-format
-msgid "Can't write gzip header error: %d"
+msgid "Failed to write gzip header. Write returned %d"
 msgstr ""
 
 #: fwrite.c:910
 #, c-format
-msgid "Compress gzip error: %d"
+msgid "Failed to compress gzip. compressbuff() returned %d"
 msgstr ""
 
 #: fwrite.c:911 fwrite.c:928
diff --git a/po/ru.po b/po/ru.po
@@ -207,7 +207,7 @@ msgstr "i[%d] = %d, что находится за пределами диапа
 #: assign.c:387
 #, c-format
 msgid "Assigning to %d row subset of %d rows\n"
-msgstr "Присвоение %d подмножеству строк%d\n"
+msgstr "Присвоение подмножеству из %d строк (всего %d)\n"
 
 #: assign.c:403
 msgid "length(LHS)==0; no columns to delete or assign RHS to."
@@ -285,7 +285,7 @@ msgstr ""
 "%d переданным столбцам присваивается пустой список (который может быть "
 "пустой data.table или data.frame, поскольку они тоже являются списками). "
 "Чтобы удалить несколько столбцов, используйте вместо этого значение NULL. "
-"Чтобы добавить несколько пустых списочных столбцов, используйте list(list())."
+"Чтобы добавить несколько пустых столбцов-списков, используйте list(list())."
 
 #: assign.c:456
 #, c-format
@@ -453,7 +453,7 @@ msgid ""
 msgstr ""
 "В правой части элемент №%d был скопирован, поскольку MAYBE_REFERENCED==%d "
 "MAYBE_SHARED==%d, но потом присваивается напрямую. length(правая_часть)==%d; "
-"length(левая_часть)==%d)\n"
+"length(левая_часть)==%d\n"
 
 #: assign.c:569
 #, c-format
@@ -2576,8 +2576,8 @@ msgid ""
 "Read %<PRIu64> rows x %d columns from %s file in %02d:%06.3f wall clock "
 "time\n"
 msgstr ""
-"Чтение %<PRIu64> строк * %d столбцов из файла %s заняло %02d:%06.3f по "
-"часам\n"
+"Чтение %<PRIu64> строк * %d столбцов из файла %s заняло %02d:%06.3f "
+"мин:с\n"
 
 #: fread.c:2733
 msgid "[12] Finalizing the datatable\n"
@@ -3371,7 +3371,7 @@ msgid ""
 "No list columns are present. Setting sep2='' otherwise quote='auto' would "
 "quote fields containing sep2.\n"
 msgstr ""
-"Нет списочных столбцов. Если задать sep2=''; в противном случае quote='auto' "
+"Нет столбцов-списков. Задаю sep2=''; в противном случае quote='auto' "
 "приведёт к тому, что поля, содержащие sep2, будут заключены в кавычки.\n"
 
 #: fwriteR.c:288
diff --git a/src/assign.c b/src/assign.c
@@ -1207,7 +1207,7 @@ void writeNA(SEXP v, const int from, const int n, const bool listNA)
     memset(RAW(v)+from, 0, n*sizeof(Rbyte));
     break;
   case LGLSXP: {
-    int *vd = (int *)LOGICAL(v);
+    int *vd = LOGICAL(v);
     for (int i=from; i<=to; ++i) vd[i] = NA_LOGICAL;
   } break;
   case INTSXP: {
diff --git a/src/coalesce.c b/src/coalesce.c
@@ -100,7 +100,7 @@ SEXP coalesce(SEXP x, SEXP inplaceArg) {
         if (val!=NA_INTEGER64) xP[i]=val; else if (final) xP[i]=finalVal;
       }
     } else {
-      double *xP = (double *)REAL(first), finalVal=NA_REAL;
+      double *xP = REAL(first), finalVal=NA_REAL;
       int k=0;
       for (int j=0; j<nval; ++j) {
         SEXP item = VECTOR_ELT(x, j+off);
diff --git a/src/fread.c b/src/fread.c
@@ -441,7 +441,7 @@ static const char* filesize_to_str(size_t fsize)
 double copyFile(size_t fileSize)  // only called in very very rare cases
 {
   double tt = wallclock();
-  mmp_copy = (char *)malloc((size_t)fileSize + 1 /* extra \0 */);
+  mmp_copy = (char *)malloc(fileSize + 1 /* extra \0 */);
   if (!mmp_copy)
     return -1.0; // # nocov
   memcpy(mmp_copy, mmp, fileSize);
diff --git a/src/freadR.c b/src/freadR.c
@@ -624,7 +624,7 @@ void pushBuffer(ThreadLocalFreadParsingContext *ctx)
     resj++;
     if (type[j]!=CT_STRING && type[j]>0) {
       if (thisSize == 8) {
-        double *dest = (double *)REAL(VECTOR_ELT(DT, resj)) + DTi;
+        double *dest = REAL(VECTOR_ELT(DT, resj)) + DTi;
         const char *src8 = (char*)buff8 + off8;
         for (int i=0; i<nRows; ++i) {
           *dest = *(double *)src8;
@@ -633,7 +633,7 @@ void pushBuffer(ThreadLocalFreadParsingContext *ctx)
         }
       } else
       if (thisSize == 4) {
-        int *dest = (int *)INTEGER(VECTOR_ELT(DT, resj)) + DTi;
+        int *dest = INTEGER(VECTOR_ELT(DT, resj)) + DTi;
         const char *src4 = (char*)buff4 + off4;
         // debug line for #3369 ... if (DTi>2638000) printf("freadR.c:460: thisSize==4, resj=%d, %"PRIu64", %d, %d, j=%d, done=%d\n", resj, (uint64_t)DTi, off4, rowSize4, j, done);
         for (int i=0; i<nRows; ++i) {
diff --git a/src/fwrite.c b/src/fwrite.c
@@ -906,8 +906,8 @@ void fwriteMain(fwriteMainArgs args)
 #ifndef NOZLIB
         free(zbuffPool);
 #endif
-        if (ret0 == -1) STOP(_("Can't write gzip header error: %d"), ret0);
-        else if (ret1) STOP(_("Compress gzip error: %d"), ret1);
+        if (ret0 == -1) STOP(_("Failed to write gzip header. Write returned %d"), ret0);
+        else if (ret1) STOP(_("Failed to compress gzip. compressbuff() returned %d"), ret1);
         else STOP(_("%s: '%s'"), strerror(errwrite), args.filename);
         // # nocov end
       }
diff --git a/src/ijoin.c b/src/ijoin.c
@@ -10,8 +10,8 @@ SEXP lookup(SEXP ux, SEXP xlen, SEXP indices, SEXP gaps, SEXP overlaps, SEXP mul
 
   SEXP vv, tt, lookup, type_lookup;
   R_len_t *idx,*count,*type_count,xrows=INTEGER(xlen)[0],uxrows=LENGTH(VECTOR_ELT(ux, 0)),uxcols=LENGTH(ux);
-  int *from = (int *)INTEGER(VECTOR_ELT(indices, 0));
-  int *to   = (int *)INTEGER(VECTOR_ELT(indices, 1));
+  int *from = INTEGER(VECTOR_ELT(indices, 0));
+  int *to   = INTEGER(VECTOR_ELT(indices, 1));
   clock_t pass1, pass2, pass3, start;
   enum {ALL, FIRST, LAST} mult = ALL;
   enum {ANY, WITHIN, START, END, EQUAL} type = ANY;
@@ -31,8 +31,8 @@ SEXP lookup(SEXP ux, SEXP xlen, SEXP indices, SEXP gaps, SEXP overlaps, SEXP mul
   // For reference: uxcols-1 = type_count, uxcols-2 = count, uxcols-3 = type_lookup, uxcols-4 = lookup
   // first pass: calculate lengths first
   start = clock();
-  count = (int *)INTEGER(VECTOR_ELT(ux, uxcols-2));
-  type_count = (int *)INTEGER(VECTOR_ELT(ux, uxcols-1));
+  count = INTEGER(VECTOR_ELT(ux, uxcols-2));
+  type_count = INTEGER(VECTOR_ELT(ux, uxcols-1));
   switch (mult) {
   case FIRST:
     switch(type) {
@@ -225,10 +225,10 @@ SEXP overlaps(SEXP ux, SEXP imatches, SEXP multArg, SEXP typeArg, SEXP nomatchAr
 
   R_len_t uxcols=LENGTH(ux),rows=length(VECTOR_ELT(imatches,0));
   int nomatch = INTEGER(nomatchArg)[0], totlen=0, thislen;
-  int *from   = (int *)INTEGER(VECTOR_ELT(imatches, 0));
-  int *to     = (int *)INTEGER(VECTOR_ELT(imatches, 1));
-  int *count   = (int *)INTEGER(VECTOR_ELT(ux, uxcols-2));
-  int *type_count   = (int *)INTEGER(VECTOR_ELT(ux, uxcols-1));
+  int *from   = INTEGER(VECTOR_ELT(imatches, 0));
+  int *to     = INTEGER(VECTOR_ELT(imatches, 1));
+  int *count   = INTEGER(VECTOR_ELT(ux, uxcols-2));
+  int *type_count   = INTEGER(VECTOR_ELT(ux, uxcols-1));
   SEXP lookup = VECTOR_ELT(ux, uxcols-4);
   SEXP type_lookup = VECTOR_ELT(ux, uxcols-3);
   SEXP ans, f1__, f2__, tmp1, tmp2;
diff --git a/src/negate.c b/src/negate.c
@@ -5,7 +5,7 @@ void negateByRef(SEXP x) {
     error("not logical or integer vector");  // # nocov
   }
   const int n = length(x);
-  int *ansd = (int *)LOGICAL(x);
+  int *ansd = LOGICAL(x);
   for(int i=0; i<n; ++i) {
     ansd[i] ^= (ansd[i] != NA_LOGICAL);  // invert true/false but leave NA alone
   }
diff --git a/src/reorder.c b/src/reorder.c
@@ -63,7 +63,7 @@ SEXP reorder(SEXP x, SEXP order)
     // This check is once up front, and then idx is applied to all the columns which is where the most time is spent.
   }
 
-  char *TMP = (char *)R_alloc(nmid, maxSize);
+  char *TMP = R_alloc(nmid, maxSize);
 
   for (int i=0; i<ncol; ++i) {
     const SEXP v = isNewList(x) ? VECTOR_ELT(x,i) : x;
diff --git a/vignettes/datatable-intro.Rmd b/vignettes/datatable-intro.Rmd
@@ -316,7 +316,7 @@ ans
 
 We could have accomplished the same operation by doing `nrow(flights[origin == "JFK" & month == 6L])`. However, it would have to subset the entire `data.table` first corresponding to the *row indices* in `i` *and then* return the rows using `nrow()`, which is unnecessary and inefficient. We will cover this and other optimisation aspects in detail under the *`data.table` design* vignette.
 
-### h) Great! But how can I refer to columns by names in `j` (like in a `data.frame`)? {#refer_j}
+### h) Great! But how can I refer to columns by names in `j` (like in a `data.frame`)? {#refer-j}
 
 If you're writing out the column names explicitly, there's no difference compared to a `data.frame` (since v1.9.8).
 
@@ -422,7 +422,7 @@ ans
 
     We'll use this convenient form wherever applicable hereafter.
 
-#### -- How can we calculate the number of trips for each origin airport for carrier code `"AA"`? {#origin-.N}
+#### -- How can we calculate the number of trips for each origin airport for carrier code `"AA"`? {#origin-N}
 
 The unique carrier code `"AA"` corresponds to *American Airlines Inc.*
 
@@ -435,7 +435,7 @@ ans
 
 * Using those *row indices*, we obtain the number of rows while grouped by `origin`. Once again no columns are actually materialised here, because the `j-expression` does not require any columns to be actually subsetted and is therefore fast and memory efficient.
 
-#### -- How can we get the total number of trips for each `origin, dest` pair for carrier code `"AA"`? {#origin-dest-.N}
+#### -- How can we get the total number of trips for each `origin, dest` pair for carrier code `"AA"`? {#origin-dest-N}
 
 ```{r}
 ans <- flights[carrier == "AA", .N, by = .(origin, dest)]
@@ -483,7 +483,7 @@ We'll learn more about `keys` in the [`vignette("datatable-keys-fast-subset", pa
 
 ### c) Chaining
 
-Let's reconsider the task of [getting the total number of trips for each `origin, dest` pair for carrier *"AA"*](#origin-dest-.N).
+Let's reconsider the task of [getting the total number of trips for each `origin, dest` pair for carrier *"AA"*](#origin-dest-N).
 
 ```{r}
 ans <- flights[carrier == "AA", .N, by = .(origin, dest)]
@@ -583,7 +583,7 @@ We are almost there. There is one little thing left to address. In our `flights`
 
 Using the argument `.SDcols`. It accepts either column names or column indices. For example, `.SDcols = c("arr_delay", "dep_delay")` ensures that `.SD` contains only these two columns for each group.
 
-Similar to [part g)](#refer_j), you can also specify the columns to remove instead of columns to keep using `-` or `!`. Additionally, you can select consecutive columns as `colA:colB` and deselect them as `!(colA:colB)` or `-(colA:colB)`.
+Similar to [part g)](#refer-j), you can also specify the columns to remove instead of columns to keep using `-` or `!`. Additionally, you can select consecutive columns as `colA:colB` and deselect them as `!(colA:colB)` or `-(colA:colB)`.
 
 Now let us try to use `.SD` along with `.SDcols` to get the `mean()` of `arr_delay` and `dep_delay` columns grouped by `origin`, `dest` and `month`.
 
diff --git a/vignettes/fr/datatable-intro.Rmd b/vignettes/fr/datatable-intro.Rmd
@@ -312,7 +312,7 @@ ans
 
 On aurait pu faire la même opération en écrivant `nrow(flights[origin == "JFK" & month == 6L])`. Néanmoins il aurait fallu d'abord dissocier la `data.table` entière  en fonction des *indices de lignes* dans `i` *puis* renvoyer les lignes en utilisant `nrow()`, ce qui est inutile et pas efficace. Nous aborderons en détails ce sujet et d'autres aspects de l'optimisation dans la vignette *architecture de `data.table`*.
 
-### h) Super !  Mais comment référencer les colonnes par nom dans `j` (comme avec un `data.frame`) ? {#refer_j}
+### h) Super !  Mais comment référencer les colonnes par nom dans `j` (comme avec un `data.frame`) ? {#refer-j}
 
 Si vous imprimez le nom des colonnes explicitement, il n'y a pas de différence avec un `data.frame` (depuis v1.9.8).
 
@@ -418,7 +418,7 @@ ans
     
     Nous utiliserons cette forme pratique chaque fois que cela sera possible.
 
-#### -- Comment calculer le nombre de voyages au départ de chaque aéroport pour le transporteur ayant le code `"AA"`? {#origin-.N}
+#### -- Comment calculer le nombre de voyages au départ de chaque aéroport pour le transporteur ayant le code `"AA"`? {#origin-N}
 
 Le code unique de transporteur `"AA"` correspond à *American Airlines Inc.*
 
@@ -431,7 +431,7 @@ ans
 
 * En utilisant ces *index de ligne*, nous obtenons le nombre de lignes groupées par `origine`. Une fois de plus, aucune colonne n'est matérialisée ici, car l'expression `j' ne nécessite aucune colonne pour définir le sous-ensemble et le calcul est donc rapide et peu gourmand en mémoire.
 
-#### -- Comment obtenir le nombre total de voyages pour chaque paire `origin, dest` du transporteur ayant pour code `"AA"`? {#origin-dest-.N}
+#### -- Comment obtenir le nombre total de voyages pour chaque paire `origin, dest` du transporteur ayant pour code `"AA"`? {#origin-dest-N}
 
 ```{r}
 ans <- flights[carrier == "AA", .N, by = .(origin, dest)]
@@ -479,7 +479,7 @@ Nous en apprendrons plus au sujet des `clés` dans la vignette *Clés et sous-en
 
 ### c) Chaînage
 
-Considérons la tâche consistant à [récupérer le nombre total de voyages pour chaque couple `origin, dest` du transporteur *"AA"*](#origin-dest-.N).
+Considérons la tâche consistant à [récupérer le nombre total de voyages pour chaque couple `origin, dest` du transporteur *"AA"*](#origin-dest-N).
 
 ```{r}
 ans <- flights[carrier == "AA", .N, by = .(origin, dest)]
@@ -579,7 +579,7 @@ Nous y sommes presque. Il reste encore une petite chose à régler. Dans notre `
 
 En utilisant l'argument `.SDcols`. Il accepte soit des noms soit des indices de colonnes. Par exemple, `.SDcols = c("arr_delay", "dep_delay")` permet que `.SD` ne comporte que ces deux colonnes pour chaque groupe.
 
-De la même manière que [part g)](#refer_j), vous pouvez également spécifier les colonnes à supprimer au lieu des colonnes à garder en utilisant le `-` ou `!`. De plus, vous pouvez sélectionner des colonnes consécutives avec `colA:colB` et les désélectionner avec `!(colA:colB)` ou `-(colA:colB)`.
+De la même manière que [part g)](#refer-j), vous pouvez également spécifier les colonnes à supprimer au lieu des colonnes à garder en utilisant le `-` ou `!`. De plus, vous pouvez sélectionner des colonnes consécutives avec `colA:colB` et les désélectionner avec `!(colA:colB)` ou `-(colA:colB)`.
 
 Maintenant essayons d'utiliser `.SD` avec `.SDcols` pour obtenir la moyenne `mean()` des colonnes `arr_delay` et `dep_delay` groupées par `origin`, `dest` et `month`.
 

-Original file line number
+Diff line change
@@ @@ -0,0 +1,6 @@ @@
 +@@
 +type T;
 +T* E;
 +@@
 +- (T*)
 +  E