Address that tsk_size_t is uint64_t

RcppTskit/DESCRIPTION

@@ -32,6 +32,7 @@ BugReports: https://github.com/HighlanderLab/RcppTskit/issues
 Depends:
     R (>= 4.0.0)
 Imports:
+    bit64,
     methods,
     R6,
     Rcpp (>= 1.0.8),

RcppTskit/NAMESPACE

@@ -15,6 +15,8 @@ export(tskit_version)
 importFrom(R6,R6Class)
 importFrom(Rcpp,cppFunction)
 importFrom(Rcpp,registerPlugin)
+importFrom(bit64,as.integer64)
+importFrom(bit64,is.integer64)
 importFrom(methods,is)
 importFrom(reticulate,import)
 importFrom(reticulate,is_py_object)

RcppTskit/NEWS.md

@@ -39,6 +39,9 @@ and releases adhere to [Semantic Versioning](https://semver.org/spec/v2.0.0.html
   constructor argument from `pointer` to `xptr`.
 - Ensured `TableCollection$tree_sequence()` matches `tskit Python` API:
   it now builds indexes on the `TableCollection`, if indexes are not present.
+- We now use `bit64::integer64` (signed 64 bit integer) instead of `int` aiming
+  to approach `tsk_size_t` in `tskit C` (unsigned 64 bit integer); in low-level
+  `rtsk_treeseq_get_num_*()` wrappers and count/metadata-length fields.
 - TODO
 
 ### Maintenance

RcppTskit/R/RcppExports.R

@@ -1,6 +1,14 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
+test_validate_options <- function(options, supported) {
+    .Call(`_RcppTskit_test_validate_options`, options, supported)
+}
+
+test_rtsk_wrap_tsk_size_t_as_integer64 <- function(value, force_range_error = FALSE) {
+    .Call(`_RcppTskit_test_rtsk_wrap_tsk_size_t_as_integer64`, value, force_range_error)
+}
+
 #' @title Report the version of installed kastore C API
 #' @details The version is stored in the installed header \code{kastore.h}.
 #' @return A named vector with three elements \code{major}, \code{minor}, and

RcppTskit/R/RcppTskit-package.R

@@ -20,6 +20,7 @@
 #' @keywords internal
 #'
 #' @useDynLib RcppTskit, .registration = TRUE
+#' @importFrom bit64 as.integer64 is.integer64
 #' @importFrom methods is
 #' @importFrom R6 R6Class
 #' @importFrom Rcpp cppFunction registerPlugin

RcppTskit/R/RcppTskit.R

@@ -214,7 +214,9 @@ tc_read <- tc_load
 #   compared to Python API, so also not available here.
 # @return A list with two data.frames; the first contains tree sequence
 #   properties and their value; the second contains the numbers of rows in
-#   tables and the length of their metadata.
+#   tables and the length of their metadata. All columns are character as they
+#   contain different types of values. Use specific functions if you want to
+#   obtain non-character values
 # @seealso \code{\link[=TreeSequence]{TreeSequence$print}} on how this
 #   function is used and presented to users.
 # @examples
@@ -243,17 +245,17 @@ rtsk_treeseq_print <- function(ts) {
         "file_uuid"
       ),
       value = c(
-        tmp_summary[["num_samples"]],
-        tmp_summary[["num_trees"]],
-        tmp_summary[["sequence_length"]],
-        tmp_summary[["discrete_genome"]],
-        tmp_summary[["has_reference_sequence"]],
-        tmp_summary[["time_units"]],
-        tmp_summary[["discrete_time"]],
-        tmp_summary[["min_time"]],
-        tmp_summary[["max_time"]],
-        tmp_metadata[["ts"]] > 0,
-        tmp_summary[["file_uuid"]]
+        as.character(tmp_summary[["num_samples"]]),
+        as.character(tmp_summary[["num_trees"]]),
+        as.character(tmp_summary[["sequence_length"]]),
+        as.character(tmp_summary[["discrete_genome"]]),
+        as.character(tmp_summary[["has_reference_sequence"]]),
+        as.character(tmp_summary[["time_units"]]),
+        as.character(tmp_summary[["discrete_time"]]),
+        as.character(tmp_summary[["min_time"]]),
+        as.character(tmp_summary[["max_time"]]),
+        as.character(tmp_metadata[["ts"]] > 0),
+        as.character(tmp_summary[["file_uuid"]])
       )
     ),
     tables = data.frame(
@@ -268,24 +270,24 @@ rtsk_treeseq_print <- function(ts) {
         "mutations"
       ),
       number = c(
-        tmp_summary[["num_provenances"]],
-        tmp_summary[["num_populations"]],
-        tmp_summary[["num_migrations"]],
-        tmp_summary[["num_individuals"]],
-        tmp_summary[["num_nodes"]],
-        tmp_summary[["num_edges"]],
-        tmp_summary[["num_sites"]],
-        tmp_summary[["num_mutations"]]
+        as.character(tmp_summary[["num_provenances"]]),
+        as.character(tmp_summary[["num_populations"]]),
+        as.character(tmp_summary[["num_migrations"]]),
+        as.character(tmp_summary[["num_individuals"]]),
+        as.character(tmp_summary[["num_nodes"]]),
+        as.character(tmp_summary[["num_edges"]]),
+        as.character(tmp_summary[["num_sites"]]),
+        as.character(tmp_summary[["num_mutations"]])
       ),
       has_metadata = c(
         NA, # provenances have no metadata
-        tmp_metadata[["populations"]] > 0,
-        tmp_metadata[["migrations"]] > 0,
-        tmp_metadata[["individuals"]] > 0,
-        tmp_metadata[["nodes"]] > 0,
-        tmp_metadata[["edges"]] > 0,
-        tmp_metadata[["sites"]] > 0,
-        tmp_metadata[["mutations"]] > 0
+        as.character(tmp_metadata[["populations"]] > 0),
+        as.character(tmp_metadata[["migrations"]] > 0),
+        as.character(tmp_metadata[["individuals"]] > 0),
+        as.character(tmp_metadata[["nodes"]] > 0),
+        as.character(tmp_metadata[["edges"]] > 0),
+        as.character(tmp_metadata[["sites"]] > 0),
+        as.character(tmp_metadata[["mutations"]] > 0)
       )
     )
   )
@@ -299,7 +301,9 @@ rtsk_treeseq_print <- function(ts) {
 #   \code{\link{rtsk_table_collection_metadata_length}}.
 # @return A list with two data.frames; the first contains table collection
 #   properties and their value; the second contains the numbers of rows in
-#   tables and the length of their metadata.
+#   tables and the length of their metadata.  All columns are character as they
+#   contain different types of values. Use specific functions if you want to
+#   obtain non-character values
 # @seealso \code{\link[=TableCollection]{TableCollection$print}} on how this
 #   function is used and presented to users.
 # @examples
@@ -323,12 +327,12 @@ rtsk_table_collection_print <- function(tc) {
         "has_index"
       ),
       value = c(
-        tmp_summary[["sequence_length"]],
-        tmp_summary[["has_reference_sequence"]],
-        tmp_summary[["time_units"]],
-        tmp_metadata[["tc"]] > 0,
-        tmp_summary[["file_uuid"]],
-        tmp_summary[["has_index"]]
+        as.character(tmp_summary[["sequence_length"]]),
+        as.character(tmp_summary[["has_reference_sequence"]]),
+        as.character(tmp_summary[["time_units"]]),
+        as.character(tmp_metadata[["tc"]] > 0),
+        as.character(tmp_summary[["file_uuid"]]),
+        as.character(tmp_summary[["has_index"]])
       )
     ),
     tables = data.frame(
@@ -343,24 +347,24 @@ rtsk_table_collection_print <- function(tc) {
         "mutations"
       ),
       number = c(
-        tmp_summary[["num_provenances"]],
-        tmp_summary[["num_populations"]],
-        tmp_summary[["num_migrations"]],
-        tmp_summary[["num_individuals"]],
-        tmp_summary[["num_nodes"]],
-        tmp_summary[["num_edges"]],
-        tmp_summary[["num_sites"]],
-        tmp_summary[["num_mutations"]]
+        as.character(tmp_summary[["num_provenances"]]),
+        as.character(tmp_summary[["num_populations"]]),
+        as.character(tmp_summary[["num_migrations"]]),
+        as.character(tmp_summary[["num_individuals"]]),
+        as.character(tmp_summary[["num_nodes"]]),
+        as.character(tmp_summary[["num_edges"]]),
+        as.character(tmp_summary[["num_sites"]]),
+        as.character(tmp_summary[["num_mutations"]])
       ),
       has_metadata = c(
         NA, # provenances have no metadata
-        tmp_metadata[["populations"]] > 0,
-        tmp_metadata[["migrations"]] > 0,
-        tmp_metadata[["individuals"]] > 0,
-        tmp_metadata[["nodes"]] > 0,
-        tmp_metadata[["edges"]] > 0,
-        tmp_metadata[["sites"]] > 0,
-        tmp_metadata[["mutations"]] > 0
+        as.character(tmp_metadata[["populations"]] > 0),
+        as.character(tmp_metadata[["migrations"]] > 0),
+        as.character(tmp_metadata[["individuals"]] > 0),
+        as.character(tmp_metadata[["nodes"]] > 0),
+        as.character(tmp_metadata[["edges"]] > 0),
+        as.character(tmp_metadata[["sites"]] > 0),
+        as.character(tmp_metadata[["mutations"]] > 0)
       )
     )
   )

RcppTskit/inst/include/RcppTskit_public.hpp

@@ -19,16 +19,16 @@ void rtsk_table_collection_dump(SEXP tc, std::string &filename,
 SEXP rtsk_treeseq_copy_tables(SEXP ts, int options = 0);
 SEXP rtsk_treeseq_init(SEXP tc, int options = 0);
 
-int rtsk_treeseq_get_num_provenances(SEXP ts);
-int rtsk_treeseq_get_num_populations(SEXP ts);
-int rtsk_treeseq_get_num_migrations(SEXP ts);
-int rtsk_treeseq_get_num_individuals(SEXP ts);
-int rtsk_treeseq_get_num_samples(SEXP ts);
-int rtsk_treeseq_get_num_nodes(SEXP ts);
-int rtsk_treeseq_get_num_edges(SEXP ts);
-int rtsk_treeseq_get_num_trees(SEXP ts);
-int rtsk_treeseq_get_num_sites(SEXP ts);
-int rtsk_treeseq_get_num_mutations(SEXP ts);
+SEXP rtsk_treeseq_get_num_provenances(SEXP ts);
+SEXP rtsk_treeseq_get_num_populations(SEXP ts);
+SEXP rtsk_treeseq_get_num_migrations(SEXP ts);
+SEXP rtsk_treeseq_get_num_individuals(SEXP ts);
+SEXP rtsk_treeseq_get_num_samples(SEXP ts);
+SEXP rtsk_treeseq_get_num_nodes(SEXP ts);
+SEXP rtsk_treeseq_get_num_edges(SEXP ts);
+SEXP rtsk_treeseq_get_num_trees(SEXP ts);
+SEXP rtsk_treeseq_get_num_sites(SEXP ts);
+SEXP rtsk_treeseq_get_num_mutations(SEXP ts);
 double rtsk_treeseq_get_sequence_length(SEXP ts);
 bool rtsk_treeseq_get_discrete_genome(SEXP ts);
 bool rtsk_treeseq_has_reference_sequence(SEXP ts);

RcppTskit/src/RcppExports.cpp

@@ -10,6 +10,30 @@ Rcpp::Rostream<true>&  Rcpp::Rcout = Rcpp::Rcpp_cout_get();
 Rcpp::Rostream<false>& Rcpp::Rcerr = Rcpp::Rcpp_cerr_get();
 #endif
 
+// test_validate_options
+int test_validate_options(const int options, const int supported);
+RcppExport SEXP _RcppTskit_test_validate_options(SEXP optionsSEXP, SEXP supportedSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject rcpp_result_gen;
+    Rcpp::RNGScope rcpp_rngScope_gen;
+    Rcpp::traits::input_parameter< const int >::type options(optionsSEXP);
+    Rcpp::traits::input_parameter< const int >::type supported(supportedSEXP);
+    rcpp_result_gen = Rcpp::wrap(test_validate_options(options, supported));
+    return rcpp_result_gen;
+END_RCPP
+}
+// test_rtsk_wrap_tsk_size_t_as_integer64
+SEXP test_rtsk_wrap_tsk_size_t_as_integer64(const std::string value, const bool force_range_error);
+RcppExport SEXP _RcppTskit_test_rtsk_wrap_tsk_size_t_as_integer64(SEXP valueSEXP, SEXP force_range_errorSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject rcpp_result_gen;
+    Rcpp::RNGScope rcpp_rngScope_gen;
+    Rcpp::traits::input_parameter< const std::string >::type value(valueSEXP);
+    Rcpp::traits::input_parameter< const bool >::type force_range_error(force_range_errorSEXP);
+    rcpp_result_gen = Rcpp::wrap(test_rtsk_wrap_tsk_size_t_as_integer64(value, force_range_error));
+    return rcpp_result_gen;
+END_RCPP
+}
 // kastore_version
 Rcpp::IntegerVector kastore_version();
 RcppExport SEXP _RcppTskit_kastore_version() {
@@ -103,7 +127,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_provenances
-int rtsk_treeseq_get_num_provenances(const SEXP ts);
+SEXP rtsk_treeseq_get_num_provenances(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_provenances(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -114,7 +138,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_populations
-int rtsk_treeseq_get_num_populations(const SEXP ts);
+SEXP rtsk_treeseq_get_num_populations(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_populations(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -125,7 +149,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_migrations
-int rtsk_treeseq_get_num_migrations(const SEXP ts);
+SEXP rtsk_treeseq_get_num_migrations(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_migrations(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -136,7 +160,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_individuals
-int rtsk_treeseq_get_num_individuals(const SEXP ts);
+SEXP rtsk_treeseq_get_num_individuals(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_individuals(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -147,7 +171,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_samples
-int rtsk_treeseq_get_num_samples(const SEXP ts);
+SEXP rtsk_treeseq_get_num_samples(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_samples(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -158,7 +182,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_nodes
-int rtsk_treeseq_get_num_nodes(const SEXP ts);
+SEXP rtsk_treeseq_get_num_nodes(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_nodes(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -169,7 +193,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_edges
-int rtsk_treeseq_get_num_edges(const SEXP ts);
+SEXP rtsk_treeseq_get_num_edges(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_edges(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -180,7 +204,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_trees
-int rtsk_treeseq_get_num_trees(const SEXP ts);
+SEXP rtsk_treeseq_get_num_trees(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_trees(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -191,7 +215,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_sites
-int rtsk_treeseq_get_num_sites(const SEXP ts);
+SEXP rtsk_treeseq_get_num_sites(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_sites(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -202,7 +226,7 @@ BEGIN_RCPP
 END_RCPP
 }
 // rtsk_treeseq_get_num_mutations
-int rtsk_treeseq_get_num_mutations(const SEXP ts);
+SEXP rtsk_treeseq_get_num_mutations(const SEXP ts);
 RcppExport SEXP _RcppTskit_rtsk_treeseq_get_num_mutations(SEXP tsSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
@@ -502,6 +526,8 @@ END_RCPP
 }
 
 static const R_CallMethodDef CallEntries[] = {
+    {"_RcppTskit_test_validate_options", (DL_FUNC) &_RcppTskit_test_validate_options, 2},
+    {"_RcppTskit_test_rtsk_wrap_tsk_size_t_as_integer64", (DL_FUNC) &_RcppTskit_test_rtsk_wrap_tsk_size_t_as_integer64, 2},
     {"_RcppTskit_kastore_version", (DL_FUNC) &_RcppTskit_kastore_version, 0},
     {"_RcppTskit_tskit_version", (DL_FUNC) &_RcppTskit_tskit_version, 0},
     {"_RcppTskit_rtsk_treeseq_load", (DL_FUNC) &_RcppTskit_rtsk_treeseq_load, 2},