update of public_suffix part

Author: schochastics

vignettes/adaR.Rmd

@@ -9,8 +9,8 @@ vignette: >
 
 ```{r, include = FALSE}
 knitr::opts_chunk$set(
-  collapse = TRUE,
-  comment = "#>"
+    collapse = TRUE,
+    comment = "#>"
 )
 ```
 
@@ -106,35 +106,35 @@ ada_url_parse("https://user_1:[email protected]:8080/dir/../api?q=1#frag")
 The function can deal with punycode and percent encoding and does generally handle all types of edge cases well.
 ```{r ada_corner}
 corner_cases <- c(
-  "https://example.com:8080", "http://user:[email protected]",
-  "http://[2001:0db8:85a3:0000:0000:8a2e:0370:7334]:8080", "https://example.com/path/to/resource?query=value&another=thing#fragment",
-  "http://sub.sub.example.com", "ftp://files.example.com:2121/download/file.txt",
-  "http://example.com/path with spaces/and&special=characters?",
-  "https://user:pa%[email protected]/path", "http://example.com/..//a/b/../c/./d.html",
-  "https://example.com:8080/over/under?query=param#and-a-fragment",
-  "http://192.168.0.1/path/to/resource", "http://3com.com/path/to/resource",
-  "http://example.com/%7Eusername/", "https://example.com/a?query=value&query=value2",
-  "https://example.com/a/b/c/..", "ws://websocket.example.com:9000/chat",
-  "https://example.com:65535/edge-case-port", "file:///home/user/file.txt",
-  "http://example.com/a/b/c/%2F%2F", "http://example.com/a/../a/../a/../a/",
-  "https://example.com/./././a/", "http://example.com:8080/a;b?c=d#e",
-  "http://@example.com", "http://example.com/@test", "http://example.com/@@@/a/b",
-  "https://example.com:0/", "http://example.com/%25path%20with%20encoded%20chars",
-  "https://example.com/path?query=%26%3D%3F%23", "http://example.com:8080/?query=value#fragment#fragment2",
-  "https://example.xn--80akhbyknj4f/path/to/resource", "https://example.co.uk/path/to/resource",
-  "http://username:pass%[email protected]", "ftp://downloads.example.edu:3030/files/archive.zip",
-  "https://example.com:8080/this/is/a/deeply/nested/path/to/a/resource",
-  "http://another-example.com/..//test/./demo.html", "https://sub2.sub1.example.org:5000/login?user=test#section2",
-  "ws://chat.example.biz:5050/livechat", "http://192.168.1.100/a/b/c/d",
-  "https://secure.example.shop/cart?item=123&quantity=5", "http://example.travel/%60%21%40%23%24%25%5E%26*()",
-  "https://example.museum/path/to/artifact?search=ancient", "ftp://secure-files.example.co:4040/files/document.docx",
-  "https://test.example.aero/booking?flight=abc123", "http://example.asia/%E2%82%AC%E2%82%AC/path",
-  "http://subdomain.example.tel/contact?name=john", "ws://game-server.example.jobs:2020/match?id=xyz",
-  "http://example.mobi/path/with/mobile/content", "https://example.name/family/tree?name=smith",
-  "http://192.168.2.2/path?query1=value1&query2=value2", "http://example.pro/professional/services",
-  "https://example.info/information/page", "http://example.int/internal/systems/login",
-  "https://example.post/postal/services", "http://example.xxx/age/verification",
-  "https://example.xxx/another/edge/case/path?with=query#and-fragment"
+    "https://example.com:8080", "http://user:[email protected]",
+    "http://[2001:0db8:85a3:0000:0000:8a2e:0370:7334]:8080", "https://example.com/path/to/resource?query=value&another=thing#fragment",
+    "http://sub.sub.example.com", "ftp://files.example.com:2121/download/file.txt",
+    "http://example.com/path with spaces/and&special=characters?",
+    "https://user:pa%[email protected]/path", "http://example.com/..//a/b/../c/./d.html",
+    "https://example.com:8080/over/under?query=param#and-a-fragment",
+    "http://192.168.0.1/path/to/resource", "http://3com.com/path/to/resource",
+    "http://example.com/%7Eusername/", "https://example.com/a?query=value&query=value2",
+    "https://example.com/a/b/c/..", "ws://websocket.example.com:9000/chat",
+    "https://example.com:65535/edge-case-port", "file:///home/user/file.txt",
+    "http://example.com/a/b/c/%2F%2F", "http://example.com/a/../a/../a/../a/",
+    "https://example.com/./././a/", "http://example.com:8080/a;b?c=d#e",
+    "http://@example.com", "http://example.com/@test", "http://example.com/@@@/a/b",
+    "https://example.com:0/", "http://example.com/%25path%20with%20encoded%20chars",
+    "https://example.com/path?query=%26%3D%3F%23", "http://example.com:8080/?query=value#fragment#fragment2",
+    "https://example.xn--80akhbyknj4f/path/to/resource", "https://example.co.uk/path/to/resource",
+    "http://username:pass%[email protected]", "ftp://downloads.example.edu:3030/files/archive.zip",
+    "https://example.com:8080/this/is/a/deeply/nested/path/to/a/resource",
+    "http://another-example.com/..//test/./demo.html", "https://sub2.sub1.example.org:5000/login?user=test#section2",
+    "ws://chat.example.biz:5050/livechat", "http://192.168.1.100/a/b/c/d",
+    "https://secure.example.shop/cart?item=123&quantity=5", "http://example.travel/%60%21%40%23%24%25%5E%26*()",
+    "https://example.museum/path/to/artifact?search=ancient", "ftp://secure-files.example.co:4040/files/document.docx",
+    "https://test.example.aero/booking?flight=abc123", "http://example.asia/%E2%82%AC%E2%82%AC/path",
+    "http://subdomain.example.tel/contact?name=john", "ws://game-server.example.jobs:2020/match?id=xyz",
+    "http://example.mobi/path/with/mobile/content", "https://example.name/family/tree?name=smith",
+    "http://192.168.2.2/path?query1=value1&query2=value2", "http://example.pro/professional/services",
+    "https://example.info/information/page", "http://example.int/internal/systems/login",
+    "https://example.post/postal/services", "http://example.xxx/age/verification",
+    "https://example.xxx/another/edge/case/path?with=query#and-fragment"
 )
 
 df <- ada_url_parse(corner_cases)
@@ -153,14 +153,16 @@ ada_has_search(corner_cases)
 
 ## Public suffic extraction
 
-The package also implements a public suffix extractor `public_suffix()`, based on a 
-lookup of the [Public Suffix List](https://publicsuffix.org/) (*The list also includes private top level domains, which we excluded from this function*).
+The package also implements a public suffix extractor public_suffix(), based on a lookup of the [Public Suffix List](https://publicsuffix.org/). 
+Note that from this list, we only include registry suffixes (e.g., com, co.uk), which are those controlled by a domain name registry and governed by ICANN.
+We do not include "private" suffixes (e.g., blogspot.com) that allow people to register subdomains. Hence, we use the term domain in the sense of "top domain under a registry suffix". 
+See <https://github.com/google/guava/wiki/InternetDomainNameExplained> for more details.
 
 ```{r public_suffix}
 urls <- c(
-  "https://subsub.sub.domain.co.uk",
-  "https://domain.api.gov.uk",
-  "https://thisisnotpart.butthisispartoftheps.kawasaki.jp"
+    "https://subsub.sub.domain.co.uk",
+    "https://domain.api.gov.uk",
+    "https://thisisnotpart.butthisispartoftheps.kawasaki.jp"
 )
 public_suffix(urls)
 ```