Merge branch 'dev'

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: RcppCWB
 Type: Package
 Title: 'Rcpp' Bindings for the 'Corpus Workbench' ('CWB')
-Version: 0.6.0
-Date: 2023-03-21
+Version: 0.6.1
+Date: 2023-06-13
 Author: Andreas Blaette [aut, cre],
   Bernard Desgraupes [aut],
   Sylvain Loiseau [aut],

NEWS.md

@@ -1,4 +1,16 @@
-# RcppCWB 0.5.5.9001-.9003
+# RcppCWB 0.6.0.9001ff
+
+* New function `region_to_strucs()` to get minimumum and maximum struc of 
+s-attribute within region provided. Works also for nested s-attributes.
+* New function `region_matrix_to_struc_matrix()`.
+* Functions `cl_cpos2lbound()` and `cl_cpos2rbound()` return NA if corpus
+position is outside stru for given s-attribute. #78.
+* Functions `cl_cpos2lbound()` and `cl_cpos2rbound()` are exposed directly from
+C++ without R wrappers, improving performance. Using the environment variable
+'CORPUS_REGISTRY' if argument `registry` is handled implicitly now.
+
+
+# RcppCWB 0.6.0
 
 * Rcpp wrappers for Corpus Library (CL) functions are exposed directly and  
 can be used in C++ functions imported using `Rcpp::sourceCpp()` or

R/RcppExports.R

@@ -37,6 +37,33 @@
     .Call(`_RcppCWB_region_matrix_context`, corpus, registry, region_matrix, p_attribute, s_attribute, boundary, left, right)
 }
 
+#' Get min and max strucs of s-attribute present in region
+#' 
+#' Look up the minimum and maximum struc of a s-attribute within a region,
+#' including scenario of nested s-attributes. If there are no regions of the
+#' s-attribute within the region, `NA` values are returned.
+#' 
+#' 
+#' @param corpus ID of a CWB corpus.
+#' @param registry Path of the registry directory. If `NULL` (default), value
+#'   of environment variable 'CORPUS_REGISTRY' will be used.
+#' @param s_attribute Name of structural attribute. The attribute may be
+#'   nested.
+#' @param region Vector with left and right corpus position of region.
+#' @return Depending whether input is a vector (argument `region`) or a matrix
+#' (argument `region_matrix`), a vector or a matrix.
+#' @param region_matrix A two-column `matrix` with regions, left corpus
+#'   positions in column 1, right corpus positions in column 2.
+#' @rdname regions_to_strucs
+region_matrix_to_struc_matrix <- function(corpus, s_attribute, region_matrix, registry = NULL) {
+    .Call(`_RcppCWB_region_matrix_to_struc_matrix`, corpus, s_attribute, region_matrix, registry)
+}
+
+#' @rdname regions_to_strucs
+region_to_strucs <- function(corpus, s_attribute, region, registry = NULL) {
+    .Call(`_RcppCWB_region_to_strucs`, corpus, s_attribute, region, registry)
+}
+
 .cwb_version <- function() {
     .Call(`_RcppCWB_cwb_version`)
 }
@@ -213,8 +240,9 @@ id_to_cpos <- function(p_attr, id) {
     .Call(`_RcppCWB_id_to_cpos`, p_attr, id)
 }
 
-.cl_cpos2lbound <- function(corpus, s_attribute, cpos, registry) {
-    .Call(`_RcppCWB__cl_cpos2lbound`, corpus, s_attribute, cpos, registry)
+#' @rdname s_attributes
+cl_cpos2lbound <- function(corpus, s_attribute, cpos, registry = NULL) {
+    .Call(`_RcppCWB_cl_cpos2lbound`, corpus, s_attribute, cpos, registry)
 }
 
 #' @rdname cl_rework
@@ -223,8 +251,11 @@ cpos_to_lbound <- function(s_attr, cpos) {
     .Call(`_RcppCWB_cpos_to_lbound`, s_attr, cpos)
 }
 
-.cl_cpos2rbound <- function(corpus, s_attribute, cpos, registry) {
-    .Call(`_RcppCWB__cl_cpos2rbound`, corpus, s_attribute, cpos, registry)
+#' @rdname s_attributes
+#' @details `cl_cpos2rbound()` and `cl_cpos2lbound()` return `NA` for values of
+#'   cpos that are outside a struc for the structural attribute given.
+cl_cpos2rbound <- function(corpus, s_attribute, cpos, registry = NULL) {
+    .Call(`_RcppCWB_cl_cpos2rbound`, corpus, s_attribute, cpos, registry)
 }
 
 #' @rdname cl_rework

R/cl.R

@@ -171,34 +171,6 @@ cl_struc2str <- function(corpus, s_attribute, struc, registry = Sys.getenv("CORP
   .cl_struc2str(corpus = corpus, s_attribute = s_attribute, struc = struc, registry = registry)
 }
 
-#' @rdname s_attributes
-cl_cpos2lbound <- function(corpus, s_attribute, cpos, registry = Sys.getenv("CORPUS_REGISTRY")){
-  check_registry(registry)
-  check_corpus(corpus, registry, cqp = FALSE)
-  check_s_attribute(corpus = corpus, registry = registry, s_attribute = s_attribute)
-
-  if (length(cpos) == 0L) return(integer())
-  check_cpos(corpus = corpus, p_attribute = "word", cpos = cpos, registry = registry)
-
-  .cl_cpos2lbound(corpus = corpus, s_attribute = s_attribute, cpos = cpos, registry = registry)
-}
-
-#' @rdname s_attributes
-cl_cpos2rbound <- function(corpus, s_attribute, cpos, registry = Sys.getenv("CORPUS_REGISTRY")){
-  check_registry(registry)
-  check_corpus(corpus, registry, cqp = FALSE)
-  check_s_attribute(corpus = corpus, registry = registry, s_attribute = s_attribute)
-
-  check_cpos(corpus = corpus, p_attribute = "word", cpos = cpos, registry = registry)
-  if (length(cpos) == 0L) return(integer())
-
-  .cl_cpos2rbound(corpus = corpus, s_attribute = s_attribute, cpos = cpos, registry = registry)
-}
-
-
-
-
-
 
 #' @title Using Positional Attributes.
 #' 
@@ -401,8 +373,7 @@ cl_charset_name <- function(corpus, registry = Sys.getenv("CORPUS_REGISTRY")){
 cl_struc_values <- function(corpus, s_attribute, registry = Sys.getenv("CORPUS_REGISTRY")){
   check_corpus(corpus = corpus, registry = registry, cqp = FALSE)
   registry <- normalizePath(path.expand(registry))
-  i <- .cl_struc_values(corpus = corpus, s_attribute = s_attribute, registry = registry)
-  if (i == 1L) TRUE else if (i == 0L) FALSE else if (i < 0L) as.integer(NA)
+  .cl_struc_values(corpus = corpus, s_attribute = s_attribute, registry = registry)
 }
 
 #' Get information from registry file
@@ -571,6 +542,7 @@ cl_list_corpora <- function(){
 #' @name cl_rework
 #' @rdname cl_rework
 #' @examples
+#' \donttest{
 #' library(Rcpp)
 #' 
 #' cppFunction(
@@ -590,6 +562,7 @@ cl_list_corpora <- function(){
 #' )
 #'
 #' result <- get_str("REUTERS", "word", RcppCWB::get_tmp_registry(), 0:50)
+#' }
 NULL
 
 

cran-comments.md

@@ -1,21 +1,10 @@
 ## General remarks
 
-- This release replaces dependency PCRE with PCRE2 in the CWB source code 
-included in this package. I hereby anticipate that build machines will 
-successively not have PCRE installed. Fedora will presumably be first.
+- This release extends auxiliary Rcpp functionality and fixes minor bugs. No 
+changes of fundamentals.
 
-- Rcpp wrappers for CWB functionality is now exported such that it is possible 
-to write Rcpp inline C++ functions using this functionality.
-
-- This is the first package version that includes a vignette (explaining how to
-write inline C++ functions). 
-
-- The cleanup script is extended and reverts modifications that had previously
-gone unnoticed. 
-
-- A failure to build Windows binaries for R-oldrel is addressed: Repository 
-https://github.com/PolMine/libcl that is used to get static libraries has been 
-updated.
+- An example using `cppFunction()` ran 10 secs on winbuilder, so I wrapped this
+into \donttest{}.
 
 Previous aspects I repeat:
 
@@ -32,8 +21,8 @@ change.
 ## Test environments
 
 * CI checks with GitHub Actions (Windows/macOS/Ubuntu)
-* R winbuilder (R 4.2 release, devel, oldrel)
-* local macOS, R 4.2.2 (arm64)
+* R winbuilder (R 4.3.0 release, devel, oldrel)
+* local macOS, R 4.3.0 (arm64)
 
 
 ## R CMD check results

inst/include/RcppCWB_RcppExports.h

@@ -612,17 +612,17 @@ namespace RcppCWB {
         return Rcpp::as<Rcpp::IntegerVector >(rcpp_result_gen);
     }
 
-    inline Rcpp::IntegerVector _cl_cpos2lbound(SEXP corpus, SEXP s_attribute, Rcpp::IntegerVector cpos, SEXP registry) {
-        typedef SEXP(*Ptr__cl_cpos2lbound)(SEXP,SEXP,SEXP,SEXP);
-        static Ptr__cl_cpos2lbound p__cl_cpos2lbound = NULL;
-        if (p__cl_cpos2lbound == NULL) {
-            validateSignature("Rcpp::IntegerVector(*_cl_cpos2lbound)(SEXP,SEXP,Rcpp::IntegerVector,SEXP)");
-            p__cl_cpos2lbound = (Ptr__cl_cpos2lbound)R_GetCCallable("RcppCWB", "_RcppCWB__cl_cpos2lbound");
+    inline Rcpp::IntegerVector cl_cpos2lbound(SEXP corpus, SEXP s_attribute, Rcpp::IntegerVector cpos, SEXP registry = R_NilValue) {
+        typedef SEXP(*Ptr_cl_cpos2lbound)(SEXP,SEXP,SEXP,SEXP);
+        static Ptr_cl_cpos2lbound p_cl_cpos2lbound = NULL;
+        if (p_cl_cpos2lbound == NULL) {
+            validateSignature("Rcpp::IntegerVector(*cl_cpos2lbound)(SEXP,SEXP,Rcpp::IntegerVector,SEXP)");
+            p_cl_cpos2lbound = (Ptr_cl_cpos2lbound)R_GetCCallable("RcppCWB", "_RcppCWB_cl_cpos2lbound");
         }
         RObject rcpp_result_gen;
         {
             RNGScope RCPP_rngScope_gen;
-            rcpp_result_gen = p__cl_cpos2lbound(Shield<SEXP>(Rcpp::wrap(corpus)), Shield<SEXP>(Rcpp::wrap(s_attribute)), Shield<SEXP>(Rcpp::wrap(cpos)), Shield<SEXP>(Rcpp::wrap(registry)));
+            rcpp_result_gen = p_cl_cpos2lbound(Shield<SEXP>(Rcpp::wrap(corpus)), Shield<SEXP>(Rcpp::wrap(s_attribute)), Shield<SEXP>(Rcpp::wrap(cpos)), Shield<SEXP>(Rcpp::wrap(registry)));
         }
         if (rcpp_result_gen.inherits("interrupted-error"))
             throw Rcpp::internal::InterruptedException();
@@ -654,17 +654,17 @@ namespace RcppCWB {
         return Rcpp::as<Rcpp::IntegerVector >(rcpp_result_gen);
     }
 
-    inline Rcpp::IntegerVector _cl_cpos2rbound(SEXP corpus, SEXP s_attribute, Rcpp::IntegerVector cpos, SEXP registry) {
-        typedef SEXP(*Ptr__cl_cpos2rbound)(SEXP,SEXP,SEXP,SEXP);
-        static Ptr__cl_cpos2rbound p__cl_cpos2rbound = NULL;
-        if (p__cl_cpos2rbound == NULL) {
-            validateSignature("Rcpp::IntegerVector(*_cl_cpos2rbound)(SEXP,SEXP,Rcpp::IntegerVector,SEXP)");
-            p__cl_cpos2rbound = (Ptr__cl_cpos2rbound)R_GetCCallable("RcppCWB", "_RcppCWB__cl_cpos2rbound");
+    inline Rcpp::IntegerVector cl_cpos2rbound(SEXP corpus, SEXP s_attribute, Rcpp::IntegerVector cpos, SEXP registry = R_NilValue) {
+        typedef SEXP(*Ptr_cl_cpos2rbound)(SEXP,SEXP,SEXP,SEXP);
+        static Ptr_cl_cpos2rbound p_cl_cpos2rbound = NULL;
+        if (p_cl_cpos2rbound == NULL) {
+            validateSignature("Rcpp::IntegerVector(*cl_cpos2rbound)(SEXP,SEXP,Rcpp::IntegerVector,SEXP)");
+            p_cl_cpos2rbound = (Ptr_cl_cpos2rbound)R_GetCCallable("RcppCWB", "_RcppCWB_cl_cpos2rbound");
         }
         RObject rcpp_result_gen;
         {
             RNGScope RCPP_rngScope_gen;
-            rcpp_result_gen = p__cl_cpos2rbound(Shield<SEXP>(Rcpp::wrap(corpus)), Shield<SEXP>(Rcpp::wrap(s_attribute)), Shield<SEXP>(Rcpp::wrap(cpos)), Shield<SEXP>(Rcpp::wrap(registry)));
+            rcpp_result_gen = p_cl_cpos2rbound(Shield<SEXP>(Rcpp::wrap(corpus)), Shield<SEXP>(Rcpp::wrap(s_attribute)), Shield<SEXP>(Rcpp::wrap(cpos)), Shield<SEXP>(Rcpp::wrap(registry)));
         }
         if (rcpp_result_gen.inherits("interrupted-error"))
             throw Rcpp::internal::InterruptedException();