Provide access to more ts/tc properties in R

Fixes #68

Author: gregorgorjanc

AGENTS.md

@@ -14,6 +14,9 @@ These notes apply to this repository root and the `RcppTskit/` package.
 * We run R CMD check for every code change.
 * We keep local quality gates green before handoff.
 * We update `RcppTskit/NEWS.md` for user-visible behavior or API changes.
+* We aim for a comparative tskit Python API and tskit R API and
+  similarly for tskit C API and tskit C++ API
+  (the later is RcppTskit C++ binding to tskit C API).
 
 ## Permission
 

RcppTskit/DESCRIPTION

@@ -12,7 +12,7 @@ Authors@R: c(
 Description: 'Tskit' enables efficient storage, manipulation, and analysis
     of ancestral recombination graphs (ARGs) using succinct tree sequence
     encoding. The tree sequence encoding of an ARG is described in Wong et
-    al. (2024) <doi:10.1093/genetics/iyae100>, while `tskit` project is
+    al. (2024) <doi:10.1093/genetics/iyae100>, while 'tskit' project is
     described in Jeffrey et al. (2026) <doi:10.48550/arXiv.2602.09649>.
     See also <https://tskit.dev> for project news, documentation, and
     tutorials. 'Tskit' provides 'Python', 'C', and 'Rust' application

RcppTskit/NEWS.md

@@ -4,6 +4,27 @@ All notable changes to RcppTskit are documented in this file.
 The file format is based on [Keep a Changelog](https://keepachangelog.com),
 and releases adhere to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added (new features)
+
+- Added the following scalar getters to match tskit C/Python API
+  - `TreeSequence$discrete_genome()` to query whether genome coordinates
+    are discrete integer values.
+  - `TreeSequence$has_reference_sequence()` to query whether a tree sequence
+    contains a reference genome sequence.
+  - `TreeSequence$discrete_time()` to query whether time values are discrete
+    integer values.
+  - `TreeSequence$file_uuid()` to query the UUID of the source `.trees` file.
+  - `TableCollection$has_reference_sequence()` to query whether a table
+    collection contains a reference genome sequence.
+  - `TableCollection$file_uuid()` to query the UUID of the source `.trees`
+    file.
+  - `TableCollection$sequence_length()` to query the sequence length.
+  - `TableCollection$time_units()` to query the time units.
+  - `TableCollection$has_index()` to query whether edge indexes are present.
+  - TODO
+
 ## [0.2.0] - 2026-02-22
 
 ### Added (new features)

RcppTskit/R/Class-TableCollection.R

@@ -14,7 +14,7 @@ TableCollection <- R6Class(
     #' @param file a string specifying the full path of the tree sequence file.
     #' @param skip_tables logical; if \code{TRUE}, load only non-table information.
     #' @param skip_reference_sequence logical; if \code{TRUE}, skip loading
-    #'   reference sequence information.
+    #'   reference genome sequence information.
     #' @param pointer an external pointer (\code{externalptr}) to a table collection.
     #' @details See the corresponding Python function at
     #'   \url{https://github.com/tskit-dev/tskit/blob/dc394d72d121c99c6dcad88f7a4873880924dd72/python/tskit/tables.py#L3463}.
@@ -88,12 +88,63 @@ TableCollection <- R6Class(
     tree_sequence = function() {
       # See https://tskit.dev/tskit/docs/stable/c-api.html#c.TSK_TS_INIT_BUILD_INDEXES
       # TSK_TS_INIT_BUILD_INDEXES (1 << 0) is bitwShiftL(1L, 0) or just 1L
-      # TODO: Should we also use https://tskit.dev/tskit/docs/stable/c-api.html#c.TSK_TS_INIT_COMPUTE_MUTATION_PARENTS?
+      # TODO: Should we also use TSK_TS_INIT_COMPUTE_MUTATION_PARENTS in TableCollection$tree_sequence()? #65
+      #       https://github.com/HighlanderLab/RcppTskit/issues/65
       init_options <- bitwShiftL(1L, 0)
       ts_ptr <- tc_ptr_to_ts_ptr(self$pointer, options = init_options)
       TreeSequence$new(pointer = ts_ptr)
     },
 
+    #' @description Get the sequence length.
+    #' @examples
+    #' tc_file <- system.file("examples/test.trees", package = "RcppTskit")
+    #' tc <- tc_load(tc_file)
+    #' tc$sequence_length()
+    sequence_length = function() {
+      tc_ptr_sequence_length(self$pointer)
+    },
+
+    #' @description Get the time units string.
+    #' @examples
+    #' tc_file <- system.file("examples/test.trees", package = "RcppTskit")
+    #' tc <- tc_load(tc_file)
+    #' tc$time_units()
+    time_units = function() {
+      tc_ptr_time_units(self$pointer)
+    },
+
+    #' @description Get whether the table collection has edge indexes.
+    #' @examples
+    #' tc_file <- system.file("examples/test.trees", package = "RcppTskit")
+    #' tc <- tc_load(tc_file)
+    #' tc$has_index()
+    has_index = function() {
+      tc_ptr_has_index(self$pointer)
+    },
+
+    #' @description Get whether the table collection has a reference genome sequence.
+    #' @examples
+    #' tc_file1 <- system.file("examples/test.trees", package = "RcppTskit")
+    #' tc_file2 <- system.file("examples/test_with_ref_seq.trees", package = "RcppTskit")
+    #' tc1 <- tc_load(tc_file1)
+    #' tc1$has_reference_sequence()
+    #' tc2 <- tc_load(tc_file2)
+    #' tc2$has_reference_sequence()
+    has_reference_sequence = function() {
+      tc_ptr_has_reference_sequence(self$pointer)
+    },
+
+    #' @description Get the file UUID string.
+    #' @details Returns the UUID of the file the table collection was loaded from.
+    #'   If unavailable, returns \code{NA_character_}.
+    #' @examples
+    #' tc_file <- system.file("examples/test.trees", package = "RcppTskit")
+    #' tc <- tc_load(tc_file)
+    #' tc$file_uuid()
+    file_uuid = function() {
+      tc_ptr_file_uuid(self$pointer)
+    },
+
     #' @description This function saves a table collection from R to disk and
     #'   loads it into reticulate Python for use with the \code{tskit} Python API.
     #' @param tskit_module reticulate Python module of \code{tskit}. By default,

RcppTskit/R/Class-TreeSequence.R

@@ -15,7 +15,7 @@ TreeSequence <- R6Class(
     #' @param file a string specifying the full path of the tree sequence file.
     #' @param skip_tables logical; if \code{TRUE}, load only non-table information.
     #' @param skip_reference_sequence logical; if \code{TRUE}, skip loading
-    #'   reference sequence information.
+    #'   reference genome sequence information.
     #' @param pointer an external pointer (\code{externalptr}) to a tree sequence.
     #' @details See the corresponding Python function at
     #'   \url{https://tskit.dev/tskit/docs/latest/python-api.html#tskit.load}.
@@ -252,6 +252,32 @@ TreeSequence <- R6Class(
       ts_ptr_sequence_length(self$pointer)
     },
 
+    #' @description Get the discrete genome status.
+    #' @details Returns \code{TRUE} if all genomic coordinates in the tree
+    #'   sequence are discrete integer values.
+    #' @examples
+    #' ts_file1 <- system.file("examples/test.trees", package = "RcppTskit")
+    #' ts_file2 <- system.file("examples/test_non_discrete_genome.trees", package = "RcppTskit")
+    #' ts1 <- ts_load(ts_file1)
+    #' ts1$discrete_genome()
+    #' ts2 <- ts_load(ts_file2)
+    #' ts2$discrete_genome()
+    discrete_genome = function() {
+      ts_ptr_discrete_genome(self$pointer)
+    },
+
+    #' @description Get whether the tree sequence has a reference genome sequence.
+    #' @examples
+    #' ts_file1 <- system.file("examples/test.trees", package = "RcppTskit")
+    #' ts_file2 <- system.file("examples/test_with_ref_seq.trees", package = "RcppTskit")
+    #' ts1 <- ts_load(ts_file1)
+    #' ts1$has_reference_sequence()
+    #' ts2 <- ts_load(ts_file2)
+    #' ts2$has_reference_sequence()
+    has_reference_sequence = function() {
+      ts_ptr_has_reference_sequence(self$pointer)
+    },
+
     #' @description Get the time units string.
     #' @examples
     #' ts_file <- system.file("examples/test.trees", package = "RcppTskit")
@@ -261,6 +287,20 @@ TreeSequence <- R6Class(
       ts_ptr_time_units(self$pointer)
     },
 
+    #' @description Get the discrete time status.
+    #' @details Returns \code{TRUE} if all time values in the tree sequence are
+    #'   discrete integer values.
+    #' @examples
+    #' ts_file1 <- system.file("examples/test.trees", package = "RcppTskit")
+    #' ts_file2 <- system.file("examples/test_discrete_time.trees", package = "RcppTskit")
+    #' ts1 <- ts_load(ts_file1)
+    #' ts1$discrete_time()
+    #' ts2 <- ts_load(ts_file2)
+    #' ts2$discrete_time()
+    discrete_time = function() {
+      ts_ptr_discrete_time(self$pointer)
+    },
+
     #' @description Get the min time in node table and mutation table.
     #' @examples
     #' ts_file <- system.file("examples/test.trees", package = "RcppTskit")
@@ -287,6 +327,17 @@ TreeSequence <- R6Class(
     #' ts$metadata_length()
     metadata_length = function() {
       ts_ptr_metadata_length(self$pointer)
+    },
+
+    #' @description Get the file UUID string.
+    #' @details Returns the UUID of the file the tree sequence was loaded from.
+    #'   If unavailable, returns \code{NA_character_}.
+    #' @examples
+    #' ts_file <- system.file("examples/test.trees", package = "RcppTskit")
+    #' ts <- ts_load(ts_file)
+    #' ts$file_uuid()
+    file_uuid = function() {
+      ts_ptr_file_uuid(self$pointer)
     }
   )
 )

RcppTskit/R/RcppExports.R

@@ -91,10 +91,22 @@ ts_ptr_sequence_length <- function(ts) {
     .Call(`_RcppTskit_ts_ptr_sequence_length`, ts)
 }
 
+ts_ptr_discrete_genome <- function(ts) {
+    .Call(`_RcppTskit_ts_ptr_discrete_genome`, ts)
+}
+
+ts_ptr_has_reference_sequence <- function(ts) {
+    .Call(`_RcppTskit_ts_ptr_has_reference_sequence`, ts)
+}
+
 ts_ptr_time_units <- function(ts) {
     .Call(`_RcppTskit_ts_ptr_time_units`, ts)
 }
 
+ts_ptr_discrete_time <- function(ts) {
+    .Call(`_RcppTskit_ts_ptr_discrete_time`, ts)
+}
+
 ts_ptr_min_time <- function(ts) {
     .Call(`_RcppTskit_ts_ptr_min_time`, ts)
 }
@@ -103,18 +115,42 @@ ts_ptr_max_time <- function(ts) {
     .Call(`_RcppTskit_ts_ptr_max_time`, ts)
 }
 
-ts_ptr_summary <- function(ts) {
-    .Call(`_RcppTskit_ts_ptr_summary`, ts)
+ts_ptr_file_uuid <- function(ts) {
+    .Call(`_RcppTskit_ts_ptr_file_uuid`, ts)
 }
 
-tc_ptr_summary <- function(tc) {
-    .Call(`_RcppTskit_tc_ptr_summary`, tc)
+ts_ptr_summary <- function(ts) {
+    .Call(`_RcppTskit_ts_ptr_summary`, ts)
 }
 
 ts_ptr_metadata_length <- function(ts) {
     .Call(`_RcppTskit_ts_ptr_metadata_length`, ts)
 }
 
+tc_ptr_sequence_length <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_sequence_length`, tc)
+}
+
+tc_ptr_has_reference_sequence <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_has_reference_sequence`, tc)
+}
+
+tc_ptr_time_units <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_time_units`, tc)
+}
+
+tc_ptr_file_uuid <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_file_uuid`, tc)
+}
+
+tc_ptr_has_index <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_has_index`, tc)
+}
+
+tc_ptr_summary <- function(tc) {
+    .Call(`_RcppTskit_tc_ptr_summary`, tc)
+}
+
 tc_ptr_metadata_length <- function(tc) {
     .Call(`_RcppTskit_tc_ptr_metadata_length`, tc)
 }