Merge branch 'master' of github.com:gaborcsardi/franc

Author: gaborcsardi

inst/README.Rmd

@@ -10,8 +10,9 @@ knitr::opts_chunk$set(
 
 > Detect the Language of Text
 
-[![Linux Build Status](https://travis-ci.org/gaborcsardi/franc.svg?branch=master)](https://travis-ci.org/gaborcsardi/franc)
-[![Windows Build status](https://ci.appveyor.com/api/projects/status/github/gaborcsardi/franc?svg=true)](https://ci.appveyor.com/project/gaborcsardi/franc)
+[![Linux Build Status](https://travis-ci.org/MangoTheCat/franc.svg?branch=master)](https://travis-ci.org/MangoTheCat/franc)
+[![Windows Build
+status](https://ci.appveyor.com/api/projects/status/github/mangothecat/franc?svg=true)](https://ci.appveyor.com/project/gaborcsardi/franc)
 [![](http://www.r-pkg.org/badges/version/franc)](http://www.r-pkg.org/pkg/franc)
 [![CRAN RStudio mirror downloads](http://cranlogs.r-pkg.org/badges/franc)](http://www.r-pkg.org/pkg/franc)
 
@@ -23,7 +24,7 @@ https://github.com/wooorm/franc.
 ## Installation
 
 ```{r eval = FALSE}
-devtools::install_github("gaborcsardi/franc")
+devtools::install_github("mangothecat/franc")
 ```
 
 ## Usage
@@ -62,7 +63,7 @@ head(franc_all("O Brasil caiu 26 posições",
 
 The R version of franc supports 310 languages. By default only the
 languages with more than 1 million speakers are used, this is 175
-languages. The \code{min_speakers} argument can relax this, and allows
+languages. The `min_speakers` argument can relax this, and allows
 using more languages:
 
 ```{r}
@@ -72,5 +73,5 @@ head(franc_all("O Brasil caiu 26 posições", min_speakers = 0))
 
 ## License
 
-MIT © Gábor Csárdi, Titus Wormer, Maciej Ceglowski, Jacob R. Rideout
-and Kent S. Johnson.
+MIT © [Mango Solutions](https://github.com/mangothecat), Titus Wormer,
+Maciej Ceglowski, Jacob R. Rideout and Kent S. Johnson.

inst/README.md

@@ -5,8 +5,9 @@
 
 > Detect the Language of Text
 
-[![Linux Build Status](https://travis-ci.org/gaborcsardi/franc.svg?branch=master)](https://travis-ci.org/gaborcsardi/franc)
-[![Windows Build status](https://ci.appveyor.com/api/projects/status/github/gaborcsardi/franc?svg=true)](https://ci.appveyor.com/project/gaborcsardi/franc)
+[![Linux Build Status](https://travis-ci.org/MangoTheCat/franc.svg?branch=master)](https://travis-ci.org/MangoTheCat/franc)
+[![Windows Build
+status](https://ci.appveyor.com/api/projects/status/github/mangothecat/franc?svg=true)](https://ci.appveyor.com/project/gaborcsardi/franc)
 [![](http://www.r-pkg.org/badges/version/franc)](http://www.r-pkg.org/pkg/franc)
 [![CRAN RStudio mirror downloads](http://cranlogs.r-pkg.org/badges/franc)](http://www.r-pkg.org/pkg/franc)
 
@@ -19,7 +20,7 @@ https://github.com/wooorm/franc.
 
 
 ```r
-devtools::install_github("gaborcsardi/franc")
+devtools::install_github("mangothecat/franc")
 ```
 
 ## Usage
@@ -125,7 +126,7 @@ head(franc_all("O Brasil caiu 26 posições",
 
 The R version of franc supports 310 languages. By default only the
 languages with more than 1 million speakers are used, this is 175
-languages. The \code{min_speakers} argument can relax this, and allows
+languages. The `min_speakers` argument can relax this, and allows
 using more languages:
 
 
@@ -159,5 +160,5 @@ head(franc_all("O Brasil caiu 26 posições", min_speakers = 0))
 
 ## License
 
-MIT © Gábor Csárdi, Titus Wormer, Maciej Ceglowski, Jacob R. Rideout
-and Kent S. Johnson.
+MIT © [Mango Solutions](https://github.com/mangothecat), Titus Wormer,
+Maciej Ceglowski, Jacob R. Rideout and Kent S. Johnson.

tests/testthat/test-franc.R

@@ -4,16 +4,14 @@ context("Language detection")
 test_that("top language is detected correctly", {
 
   expect_equal(franc("Alle menslike wesens word vry"), "afr")
-  expect_equal(franc("এটি একটি ভাষা একক IBM স্ক্রিপ্ট"), "ben")
-  expect_equal(franc("Alle mennesker er født frie og"), "nno")
   expect_equal(franc(""), "und")
   expect_equal(franc("the"), "und")
   expect_equal(franc("the", min_length = 3), "sco")
 })
 
 test_that("language scores are calculated correctly", {
 
-  scores <- franc_all('O Brasil caiu 26 posições')
+  scores <- franc_all('O Brasil caiu 26 posi\u00c7\u00f5es')
 
   expect_equal(
     scores[1:12,],

tests/testthat/test-scripts.R

@@ -5,5 +5,11 @@ test_that("script detection works", {
 
   expect_equal(get_top_script(""), NULL)
   expect_equal(get_top_script("this is in English"), "Latin")
-  expect_equal(get_top_script("এটি একটি ভাষা একক IBM স্ক্রিপ্ট"), "ben")
+
+  ben <- paste0(
+    "\u098F\u099F\u09BF \u098F\u0995\u099F\u09BF ",
+    "\u09AD\u09BE\u09B7\u09BE \u098F\u0995\u0995 IBM ",
+    "\u09B8\u09CD\u0995\u09CD\u09B0\u09BF\u09AA\u09CD\u099F"
+  )
+  expect_equal(get_top_script(ben), "ben")
 })

tests/testthat/test-trigrams.R

@@ -45,16 +45,28 @@ test_that("clean_trigrams is case insensitive", {
 
 test_that("clean_trigrams keeps UniCode letters", {
 
-  expect_equal(clean_trigrams("এটি একটি ভাষা একক IBM স্ক্রিপ্ট")[[1]],
-               c(" এট", "এটি", "টি ", "ি এ", " এক", "একট",
-                 "কটি", "টি ", "ি ভ", " ভা", "ভাষ", "াষা",
-                 "ষা ", "া এ", " এক", "একক", "কক ", "ক i",
-                 " ib", "ibm", "bm ", "m স", " স্", "স্ক", "্ক্",
-                 "ক্র", "্রি", "রিপ", "িপ্", "প্ট",
-                 "্ট "))
+  ben <- paste0(
+    "\u098F\u099F\u09BF \u098F\u0995\u099F\u09BF ",
+    "\u09AD\u09BE\u09B7\u09BE \u098F\u0995\u0995 IBM ",
+    "\u09B8\u09CD\u0995\u09CD\u09B0\u09BF\u09AA\u09CD\u099F"
+  )
+  expect_equal(
+    clean_trigrams(ben)[[1]],
+    c(" \u098F\u099F", "\u098F\u099F\u09BF", "\u099F\u09BF ",
+      "\u09BF \u098F", " \u098F\u0995", "\u098F\u0995\u099F",
+      "\u0995\u099F\u09BF", "\u099F\u09BF ", "\u09BF \u09AD",
+      " \u09AD\u09BE", "\u09AD\u09BE\u09B7",
+      "\u09BE\u09B7\u09BE", "\u09B7\u09BE ",
+      "\u09BE \u098F", " \u098F\u0995", "\u098F\u0995\u0995",
+      "\u0995\u0995 ", "\u0995 i", " ib", "ibm", "bm ",
+      "m \u09B8", " \u09B8\u09CD", "\u09B8\u09CD\u0995",
+      "\u09CD\u0995\u09CD", "\u0995\u09CD\u09B0",
+                 "\u09CD\u09B0\u09BF", "\u09B0\u09BF\u09AA",
+      "\u09BF\u09AA\u09CD", "\u09AA\u09CD\u099F",
+      "\u09CD\u099F ")
+  )
 })
 
-
 test_that("clean_trigrams removed excesive whitespace", {
 
   expect_equal(clean_trigrams("    a     ")[[1]], c(" a "))

tests/testthat/test-utils.R

@@ -8,5 +8,10 @@ test_that("match_length works", {
   expect_equal(match_length("[a-z]", ""), 0)
   expect_equal(match_length("[a-z]", "123"), 0)
 
-  expect_equal(match_length(expressions$ben, "এটি একটি ভাষা একক IBM স্ক্রিপ্ট"), 23)
+  ben <- paste0(
+    "\u098F\u099F\u09BF \u098F\u0995\u099F\u09BF ",
+    "\u09AD\u09BE\u09B7\u09BE \u098F\u0995\u0995 IBM ",
+    "\u09B8\u09CD\u0995\u09CD\u09B0\u09BF\u09AA\u09CD\u099F"
+  )
+  expect_equal(match_length(expressions$ben, ben), 23)
 })