Bahadzie/issue7 (#8)

* Handles text containing leading or trailing whitespace.
Fixes #7

* Undo unnecessary changes in English word mappings

R/numberize.R

@@ -50,7 +50,8 @@ digits_from <- function(text, lang = "en") {
   )
 
   # clean and prep
-  text <- tolower(text)
+  text <- tolower(text) # converts to string as a side effect
+  text <- trimws(text)
   text <- gsub("\\sand|-|,|\\bet\\b|\\sy\\s", " ", text) # all lang
 
   if (lang == "es") {
@@ -123,7 +124,7 @@ number_from <- function(digits) {
   if (is.na(text)) {
     return(NA)
   }
-  
+
   # convert to numeric. Numeric values will pass and non numeric values will be
   # coerced to NA and converted into numbers.
   tmp_text <- suppressWarnings(as.numeric(text))
@@ -145,6 +146,7 @@ number_from <- function(digits) {
 #'
 #' @param text Vector containing spelled numbers in a supported language.
 #' @param lang The text's language. Currently one of `"en" | "fr" | "es"`.
+#' Default is "en"
 #'
 #' @return A vector of numeric values.
 #'

README.md

@@ -1,8 +1,12 @@
 
 <!-- README.md is generated from README.Rmd. Please edit that file. -->
+
 <!-- The code to render this README is stored in .github/workflows/render-readme.yaml -->
+
 <!-- Variables marked with double curly braces will be transformed beforehand: -->
+
 <!-- `packagename` is extracted from the DESCRIPTION file -->
+
 <!-- `gh_repo` is extracted via a special environment variable in GitHub Actions -->
 
 # *numberize* <img src="man/figures/logo.svg" align="right" width="120" />
@@ -21,9 +25,10 @@ status](https://www.r-pkg.org/badges/version/numberize)](https://CRAN.R-project.
 <!-- badges: end -->
 
 *numberize* is an R package to convert numbers written as English,
-French or Spanish words from `"zero"` to
-`"nine hundred and ninety nine trillion, nine hundred and ninety nine billion, nine hundred and ninety nine million, nine hundred and ninety nine thousand, nine hundred and ninety nine"`
-from a character string to a numeric value.
+French or Spanish words from `"zero"` to `"nine hundred and ninety nine
+trillion, nine hundred and ninety nine billion, nine hundred and ninety
+nine million, nine hundred and ninety nine thousand, nine hundred and
+ninety nine"` from a character string to a numeric value.
 
 <!-- This sentence is optional and can be removed -->
 
@@ -79,17 +84,17 @@ numberize(
 
 ## Related packages and Limitations
 
-- [`{numberwang}`](https://github.com/coolbutuseless/numberwang)
-  converts numbers to words and vice versa. Limitation: English only,
-  not on CRAN.
-- [`{nombre}`](https://cran.r-project.org/web/packages/nombre/index.html)
-  converts numerics into words. Limitation: English only, no word to
-  number conversion.
-- [`{english}`](https://cran.r-project.org/web/packages/english/index.html)
-  converts numerics into words. Limitation: English only, no word to
-  number conversion.
-- [`{spanish}`](https://cran.r-project.org/web/packages/spanish/index.html)
-  converts numbers to words and vice versa. Limitation: Spanish only.
+  - [`{numberwang}`](https://github.com/coolbutuseless/numberwang)
+    converts numbers to words and vice versa. Limitation: English only,
+    not on CRAN.
+  - [`{nombre}`](https://cran.r-project.org/web/packages/nombre/index.html)
+    converts numerics into words. Limitation: English only, no word to
+    number conversion.
+  - [`{english}`](https://cran.r-project.org/web/packages/english/index.html)
+    converts numerics into words. Limitation: English only, no word to
+    number conversion.
+  - [`{spanish}`](https://cran.r-project.org/web/packages/spanish/index.html)
+    converts numbers to words and vice versa. Limitation: Spanish only.
 
 *numberize* is released as a standalone package in the hope that it will
 be useful to the R community at large. *numberize* was created in

tests/testthat/test-numberize.R

@@ -64,17 +64,17 @@ test_df <- data.frame(
   )
 )
 
-test_that("translating English numbers works", {
+test_that("translating vector of English numbers works", {
   res <- numberize(test_df[["en"]])
   expect_identical(res, test_df[["num"]])
 })
 
-test_that("translating French numbers works", {
+test_that("translating vector of French numbers works", {
   res <- numberize(test_df[["fr"]], lang = "fr")
   expect_identical(res, test_df[["num"]])
 })
 
-test_that("translating Spanish numbers works", {
+test_that("translating vector of Spanish numbers works", {
   res <- numberize(test_df[["es"]], lang = "es")
   expect_identical(res, test_df[["num"]])
 })
@@ -84,15 +84,23 @@ test_that("translating single french text works", {
   expect_identical(res, 1515)
 })
 
-test_that("non digit word returns NA", {
+
+test_that("text with non digit word returns NA", {
   res <- numberize("epiverse", lang = "en")
   expect_true(is.na(res))
 })
 
+# NB: this vector is coerced into character by R
 test_that("vector with number and words and NA is properly handled", {
   res <- numberize(
     c(17, "dix", "soixante-cinq", "deux mille vingt-quatre", NA),
     lang = "fr"
   )
   expect_identical(res, c(17, 10, 65, 2024, NA))
 })
+
+test_that("text with leading and trailing whitespace works", {
+  res <- numberize("  mille cinq  cent quinze
+    ", lang = "fr")
+  expect_identical(res, 1515)
+})