Merge branch 'master' into todoRename

Author: badasahog

.Rbuildignore

@@ -19,6 +19,7 @@
 ^\.github$
 ^\.vscode$
 ^\.zed$
+^\.lintr$
 
 ^\.gitlab-ci\.yml$
 

GOVERNANCE.md

@@ -1,4 +1,4 @@
-Governance for the R data.table project
+# Governance for the R data.table project
 
 # Purpose and scope
 
@@ -121,7 +121,7 @@ Funds acquired by the data.table project will be disbursed at the discretion of
 
 # Code of conduct
 
-The full Code of Conduct can be found [here](CODE_OF_CONDUCT.md), including details for reporting violations.
+The full Code of Conduct can be found [here](.github/CODE_OF_CONDUCT.md), including details for reporting violations.
 
 ## Reporting Responsibility
 

man/fread.Rd

@@ -118,6 +118,15 @@ Currently, the \code{yaml} setting is somewhat inflexible with respect to incorp
 
 When \code{input} begins with http://, https://, ftp://, ftps://, or file://, \code{fread} detects this and \emph{downloads} the target to a temporary file (at \code{tempfile()}) before proceeding to read the file as usual. URLS (ftps:// and https:// as well as ftp:// and http://) paths are downloaded with \code{download.file} and \code{method} set to \code{getOption("download.file.method")}, defaulting to \code{"auto"}; and file:// is downloaded with \code{download.file} with \code{method="internal"}. NB: this implies that for file://, even files found on the current machine will be "downloaded" (i.e., hard-copied) to a temporary file. See \code{\link{download.file}} for more details.
 
+\bold{Automatic Decompression:}
+
+In many cases, \code{fread} can automatically detect and decompress files with common compression extensions directly, without needing an explicit connection object or shell commands. This works by checking the file extension.
+
+  \itemize{
+    \item \code{.gz} and \code{.bz2} are supported out of the box.
+    \item \code{.zip} is also supported. If the archive contains a single data file, \code{fread} will read it. If the archive contains multiple files, \code{fread} will produce an error.
+  }
+
 \bold{Shell commands:}
 
 \code{fread} accepts shell commands for convenience. The input command is run and its output written to a file in \code{tmpdir} (\code{\link{tempdir}()} by default) to which \code{fread} is applied "as normal". The details are platform dependent -- \code{system} is used on UNIX environments, \code{shell} otherwise; see \code{\link[base]{system}}.

src/fmelt.c

@@ -282,23 +282,23 @@ SEXP checkVars(SEXP DT, SEXP id, SEXP measure, Rboolean verbose) {
 }
 
 struct processData {
-  SEXP RCHK;      // a 2 item list holding vars (result of checkVars) and not_NA_indices. PROTECTed up in fmelt so that preprocess() doesn't need to PROTECT. To pass rchk, #2865
-  SEXP idcols,    // convenience pointers into RCHK[0][0], RCHK[0][1] and RCHK[1] respectively
-    variable_table, // NULL or data for variable column(s).
-    valuecols,    // list with one element per output/value column, each element is an integer vector.
-    not_NA_indices;
-  int *isfactor,
-    *leach,       // length of each element of the valuecols(measure.vars) list.
-    *isidentical; // are all inputs for this value column the same type?
-  int lids,       // number of id columns.
-    lvars,        // number of variable columns.
-    lvalues,      // number of value columns.
-    lmax,         // max length of valuecols elements / number of times to repeat ids.
-    totlen,       // of output/long DT result of melt operation.
-    nrow;         // of input/wide DT to be melted.
+  SEXP RCHK;           // a 2 item list holding vars (result of checkVars) and not_NA_indices. PROTECTed up in fmelt so that preprocess() doesn't need to PROTECT. To pass rchk, #2865
+  SEXP idcols;         // convenience pointers into RCHK[0][0], RCHK[0][1] and RCHK[1] respectively
+  SEXP variable_table; // NULL or data for variable column(s).
+  SEXP valuecols;      // list with one element per output/value column, each element is an integer vector.
+  SEXP not_NA_indices;
+  int *isfactor;
+  int *leach;          // length of each element of the valuecols(measure.vars) list.
+  int *isidentical;    // are all inputs for this value column the same type?
+  int lids;            // number of id columns.
+  int lvars;           // number of variable columns.
+  int lvalues;         // number of value columns.
+  int lmax;            // max length of valuecols elements / number of times to repeat ids.
+  int totlen;          // of output/long DT result of melt operation.
+  int nrow;            // of input/wide DT to be melted.
   SEXPTYPE *maxtype;
-  bool measure_is_list,
-    narm;  // remove missing values?
+  bool measure_is_list;
+  bool narm;           // remove missing values?
 };
 
 static void preprocess(SEXP DT, SEXP id, SEXP measure, SEXP varnames, SEXP valnames, Rboolean narm, Rboolean verbose, struct processData *data) {

src/freadR.c

@@ -265,15 +265,13 @@ bool userOverride(int8_t *type, lenOff *colNames, const char *anchor, const int
   colNamesSxp = R_NilValue;
   SET_VECTOR_ELT(RCHK, 1, colNamesSxp = allocVector(STRSXP, ncol));
   for (int i = 0; i < ncol; i++) {
-    SEXP elem;
     if (colNames == NULL || colNames[i].len <= 0) {
       char buff[12];
       snprintf(buff, sizeof(buff), "V%d", i + 1); // # notranslate
-      elem = mkChar(buff);  // no PROTECT as passed immediately to SET_STRING_ELT
+      SET_STRING_ELT(colNamesSxp, i, mkChar(buff));  // no PROTECT as passed immediately to SET_STRING_ELT
     } else {
-      elem = mkCharLenCE(anchor + colNames[i].off, colNames[i].len, ienc);  // no PROTECT as passed immediately to SET_STRING_ELT
+      SET_STRING_ELT(colNamesSxp, i, mkCharLenCE(anchor + colNames[i].off, colNames[i].len, ienc));  // no PROTECT as passed immediately to SET_STRING_ELT
     }
-    SET_STRING_ELT(colNamesSxp, i, elem);
   }
   // "use either select= or drop= but not both" was checked earlier in freadR
   applyDrop(dropSxp, type, ncol, /*dropSource=*/-1);

src/quickselect.c

@@ -2,9 +2,9 @@
 
 // from good ol' Numerical Recipes in C
 
-static inline void iswap(int *a, int *b)           {int     tmp=*a; *a=*b; *b=tmp;}
-static inline void dswap(double *a, double *b)     {double  tmp=*a; *a=*b; *b=tmp;}
-static inline void i64swap(int64_t *a, int64_t *b) {int64_t tmp=*a; *a=*b; *b=tmp;}
+static inline void iswap(int *a, int *b)           { int     tmp = *a; *a = *b; *b = tmp; }
+static inline void dswap(double *a, double *b)     { double  tmp = *a; *a = *b; *b = tmp; }
+static inline void i64swap(int64_t *a, int64_t *b) { int64_t tmp = *a; *a = *b; *b = tmp; }
 
 #undef BODY
 #define BODY(SWAP)                          \
@@ -30,7 +30,7 @@ static inline void i64swap(int64_t *a, int64_t *b) {int64_t tmp=*a; *a=*b; *b=tm
         SWAP(x + l, x + l + 1);             \
       }                                     \
       unsigned long i = l + 1, j = ir;      \
-      a=x[l + 1];                           \
+      a = x[l + 1];                         \
       for (;;) {                            \
         do i++; while (x[i] < a);           \
         do j--; while (x[j] > a);           \
@@ -44,7 +44,7 @@ static inline void i64swap(int64_t *a, int64_t *b) {int64_t tmp=*a; *a=*b; *b=tm
     }                                       \
   }                                         \
   a = x[med];                               \
-  if (n%2 == 1) {                           \
+  if (n % 2 == 1) {                         \
     return (double)a;                       \
   } else {                                  \
     b = x[med + 1];                         \