1.1.1

Ironholds · May 7, 2015 · 17fa2dc · 17fa2dc
1 parent d38b08d
commit 17fa2dc
Show file tree

Hide file tree

Showing 5 changed files with 46 additions and 10 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: urltools
 Type: Package
 Title: Vectorised Tools for URL Handling and Parsing
-Version: 1.1.0
+Version: 1.1.1
 Date: 2015-04-11
 Author: Oliver Keyes [aut, cre], Mark Greenaway [ctb]
 Maintainer: Oliver Keyes <ironholds@gmail.com>

diff --git a/NEWS b/NEWS
@@ -1,10 +1,15 @@
-Version 1.1.1 [WIP] (maintenance release)
+Version 1.1.1
 -------------------------------------------------------------------------
 BUG FIXES
 
 * Parameter parsing now fixed to require a = after the parameter name, thus solving for scenarios where
 the URL would contain the parameter name as part of, say, the domain, and it'd grab the wrong thing. Thanks
 to Jacob Barnett for the bug report and example.
+* URL encoding no longer encodes the slash between the domain and path (thanks to Peter Meissner for pointing
+this bug out).
+
+DEVELOPMENT
+*More unit tests
 
 Version 1.1.0
 -------------------------------------------------------------------------

diff --git a/README.md b/README.md
@@ -23,14 +23,17 @@ crucial for large datasets. For more information, see the [urltools vignette](ht
 
 ###Installation
 
-The latest released version can be obtained via:
+The latest CRAN version can be obtained via:
 
     install.packages("urltools")
 
+The latest maintenance version:
+
+    devtools::install_github("ironholds/urltools", ref = "1.0.0")
+
 To get the development version:
 
-    library(devtools)
-    install_github("ironholds/urltools")
+    devtools::install_github("ironholds/urltools")
 
 ###Dependencies
 * R. Doy.

diff --git a/src/parsing.h b/src/parsing.h
@@ -88,6 +88,22 @@ class parsing{
      * part of the URL.
      */
     std::vector < std::string > url_to_vector(std::string& url_ptr);
+
+    /**
+     * Take a URL and identify the TLD in use.
+     * 
+     * @param domain_ptr a reference pointer to the domain name
+     * 
+     * @param tlds a reference pointer to the vector of
+     * TLDs
+     * 
+     * @see identify_multi_tld, the vectorised version.
+     * 
+     * @return if a match is found, {"remaining_domain_fragment","matched_tld"}.
+     * If not, {"entire_domain","Not found"}
+     */
+    std::vector < std::string > identify_single_tld (std::string& domain_ptr, std::vector < std::string >& tld_ptr);
+
   public:
 
     /**
@@ -144,6 +160,22 @@ class parsing{
      * 
      */
     DataFrame parse_to_df(std::vector < std::string >& urls_ptr);
+
+    /**
+     * Take a URL and identify the TLD in use.
+     * 
+     * @param domains_ptr a reference pointer to a vector of
+     * domain names.
+     * 
+     * @param tld_ptr a reference pointer to the vector of
+     * TLDs
+     * 
+     * @see identify_multi_tld, the vectorised version.
+     * 
+     * @return if a match is found, {"remaining_domain_fragment","matched_tld"}.
+     * If not, {"entire_domain","Not found"}
+     */
+    DataFrame identify_multi_tld_(std::vector < std::string >& domains_ptr, std::vector < std::string >& tld_ptr);
 
 };
 #endif
diff --git a/tests/testthat/test_encoding.R b/tests/testthat/test_encoding.R
@@ -4,11 +4,7 @@ test_that("Check encoding doesn't encode the scheme", {
   expect_that(url_encode("https://"), equals("https://"))
 })
 
-test_that("Check encoding does not encode domain-level slashes", {
-  expect_that(url_encode("https://foo.org/"), equals("https://foo.org/"))
-})
-
-test_that("Check encoding does encode post-domain slashes", {
+test_that("Check encoding does does not encode pre-path slashes", {
   expect_that(url_encode("https://foo.org/bar/"), equals("https://foo.org/bar%2f"))
 })