version++

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: nc
 Maintainer: Toby Dylan Hocking <[email protected]>
 Author: Toby Dylan Hocking
-Version: 2024.1.31
+Version: 2024.2.6
 License: GPL-3
 Title: Named Capture to Data Tables
 Description: User-friendly functions for extracting a data

NEWS

@@ -1,4 +1,12 @@
-Changes in version 2024.1.31
+Changes in version 2024.2.6
+
+- if(requireNamespace(suggested)) in tests, thanks CRAN.
+
+Changes in version 2024.2.1
+
+- Fix vignette 7 by adding if(requireNamespace("arrow")).
+
+Changes in version 2024.1.30
 
 - Imports data.table >= 1.15.0.
 - Remove code which uses old pre-measure data.table.

README.org

@@ -92,6 +92,9 @@ The main functions provided in nc are:
 - [[https://cloud.r-project.org/web/packages/nc/vignettes/v5-helpers.html][Vignette 5]] explains how to use helper functions for creating complex
   regular expressions.
 - [[https://cloud.r-project.org/web/packages/nc/vignettes/v6-engines.html][Vignette 6]] explains how to use different regex engines.
+- [[https://cloud.r-project.org/web/packages/nc/vignettes/v7-capture-glob.html][Vignette 7]] explains how to read regularly named files, and use a
+  regex to extract meta-data from the file names, using
+  =nc::capture_first_glob=.
 
 *** Choice of regex engine
 

tests/testthat/test-CRAN-df.R

@@ -3,7 +3,7 @@ library(testthat)
 context("df")
 source(system.file("test_engines.R", package="nc", mustWork=TRUE), local=TRUE)
 
-test_engines("default/specified engine respected", {
+if(requireNamespace("stringi"))test_engines("default/specified engine respected", {
   subject.df <- data.frame(f="foo", b="bar")
   match.dt <- capture_first_df(
     subject.df,

tests/testthat/test-CRAN-glob.R

@@ -11,7 +11,7 @@ data.chunk.pattern <- list(
   data="H.*?",
   "/",
   chunk="[0-9]+", as.integer)
-test_engines("capture_first_glob returns expected columns", {
+if(requireNamespace("R.utils"))test_engines("capture_first_glob returns expected columns", {
   count.dt <- nc::capture_first_glob(glob, data.chunk.pattern, READ=read.bedGraph)
   expect_identical(names(count.dt), c("data", "chunk", "chrom", "start", "end", "count"))
 })

tests/testthat/test-CRAN-longer.R

@@ -3,25 +3,22 @@ library(data.table)
 library(testthat)
 source(system.file("test_engines.R", package="nc", mustWork=TRUE), local=TRUE)
 
-if("measure" %in% ls(asNamespace("data.table"))){
+test_engines("single spec works", {
+  (single.spec <- nc::capture_longer_spec(iris, part=".*", "[.]", dim=".*", values_to="cm"))
+  expect_identical(sort(names(single.spec)), c(".name", ".value", "dim", "part"))
+})
 
-  test_engines("single spec works", {
-    (single.spec <- nc::capture_longer_spec(iris, part=".*", "[.]", dim=".*", values_to="cm"))
-    expect_identical(sort(names(single.spec)), c(".name", ".value", "dim", "part"))
-  })
+test_engines("multiple spec works", {
+  (multiple.spec <- nc::capture_longer_spec(iris, part=".*", "[.]", column=".*"))
+  expect_identical(sort(names(multiple.spec)), c(".name", ".value", "part"))
+})
 
-  test_engines("multiple spec works", {
-    (multiple.spec <- nc::capture_longer_spec(iris, part=".*", "[.]", column=".*"))
-    expect_identical(sort(names(multiple.spec)), c(".name", ".value", "part"))
-  })
+if(requireNamespace("tidyr"))test_engines("missing spec works", {
+  missing.col <- data.table(Sepal.Length=1, Sepal.Width=2, Petal.Length=3)
+  (missing.spec <- nc::capture_longer_spec(missing.col, part=".*", "[.]", column=".*"))
+  computed.df <- tidyr::pivot_longer_spec(missing.col, missing.spec)
+  sorted.dt <- data.table(computed.df)[order(part)]
+  expected.dt <- data.table(part=c("Petal", "Sepal"), Length=c(3, 1), Width=c(NA, 2))
+  expect_identical(sorted.dt, expected.dt)
+})
 
-  test_engines("missing spec works", {
-    missing.col <- data.table(Sepal.Length=1, Sepal.Width=2, Petal.Length=3)
-    (missing.spec <- nc::capture_longer_spec(missing.col, part=".*", "[.]", column=".*"))
-    computed.df <- tidyr::pivot_longer_spec(missing.col, missing.spec)
-    sorted.dt <- data.table(computed.df)[order(part)]
-    expected.dt <- data.table(part=c("Petal", "Sepal"), Length=c(3, 1), Width=c(NA, 2))
-    expect_identical(sorted.dt, expected.dt)
-  })
-
-}

tests/testthat/test-CRAN-measure.R

@@ -4,27 +4,24 @@ library(data.table)
 context("measure")
 source(system.file("test_engines.R", package="nc", mustWork=TRUE), local=TRUE)
 
-if("measure" %in% ls(asNamespace("data.table"))){
+DT <- data.table(a_1=10, b_2=21, a_2=20)
+test_engines("measure single value", {
+  out <- melt(DT, measure.vars=nc::measure(
+    letter="[ab]", "_", number="[12]", as.integer))
+  expected <- data.table(
+    letter=c("a","b","a"),
+    number=as.integer(c(1,2,2)),
+    value=c(10,21,20))
+  expect_identical(out, expected)
+})
 
-  DT <- data.table(a_1=10, b_2=21, a_2=20)
-  test_engines("measure single value", {
-    out <- melt(DT, measure.vars=nc::measure(
-      letter="[ab]", "_", number="[12]", as.integer))
-    expected <- data.table(
-      letter=c("a","b","a"),
-      number=as.integer(c(1,2,2)),
-      value=c(10,21,20))
-    expect_identical(out, expected)
-  })
+test_engines("measure multiple values", {
+  out <- melt(DT, measure.vars=nc::measure(
+    column="[ab]", "_", number="[12]", as.integer))
+  expected <- data.table(
+    number=as.integer(c(1,2)),
+    a=c(10,20),
+    b=c(NA,21))
+  expect_identical(out, expected)
+})
 
-  test_engines("measure multiple values", {
-    out <- melt(DT, measure.vars=nc::measure(
-      column="[ab]", "_", number="[12]", as.integer))
-    expected <- data.table(
-      number=as.integer(c(1,2)),
-      a=c(10,20),
-      b=c(NA,21))
-    expect_identical(out, expected)
-  })
-
-}

tests/testthat/test-CRAN-subject.R

@@ -23,7 +23,7 @@ test_that("capture_first_df does not use s arg for subject", {
   expect_identical(dt, expected.dt)
 })
 
-test_that("capture_melt_single does not use s arg for subject", {
+if(requireNamespace("stringi"))test_that("capture_melt_single does not use s arg for subject", {
   subject <- data.frame(family=1, s2=2, s3=3)
   ## also make sure that engine is passed thru (not interpreted as a
   ## capture group).

tests/testthat/test-CRAN-vec.R

@@ -8,7 +8,7 @@ source(system.file("test_engines.R", package="nc", mustWork=TRUE), local=TRUE)
 ## string, and an optional match that fails.
 inames <- c("Species", "Petal.Length", "Sepal.Width")
 sapply(c("[^.]*(.*)", "[^.]*([.].*)?"), function(pat){
-  stringi::stri_match_first_regex(inames, pat)
+  if(requireNamespace("stringi"))stringi::stri_match_first_regex(inames, pat)
 })
 
 test_engines("match nothing in required group is empty string", {

vignettes/v7-capture-glob.Rmd

@@ -167,7 +167,7 @@ with three variables encoded in the file path (data, chunk, part).
 The code below reads one of the files back into R:
 
 ```{r}
-data.table::fread(hive.files[1])
+  data.table::fread(hive.files[1])
 ```
 
 The output above indicates that the file only has four columns (and is missing the variables which are encoded in the file path).