Merge pull request #16845 from azat/cutToFirstSignificantSubdomainWithWWW

Add cutToFirstSignificantSubdomainWithWWW()

docs/en/sql-reference/functions/url-functions.md

@@ -115,7 +115,21 @@ Returns the “first significant subdomain”. This is a non-standard concept sp
 
 Returns the part of the domain that includes top-level subdomains up to the “first significant subdomain” (see the explanation above).
 
-For example, `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
+For example:
+
+-   `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
+-   `cutToFirstSignificantSubdomain('www.tr') = 'tr'`.
+-   `cutToFirstSignificantSubdomain('tr') = ''`.
+
+### cutToFirstSignificantSubdomainWithWWW {#cuttofirstsignificantsubdomainwithwww}
+
+Returns the part of the domain that includes top-level subdomains up to the “first significant subdomain”, without stripping "www".
+
+For example:
+
+-   `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
+-   `cutToFirstSignificantSubdomain('www.tr') = 'www.tr'`.
+-   `cutToFirstSignificantSubdomain('tr') = ''`.
 
 ### port(URL\[, default_port = 0\]) {#port}
 

src/Functions/URL/cutToFirstSignificantSubdomain.cpp

@@ -6,6 +6,7 @@
 namespace DB
 {
 
+template <bool without_www>
 struct CutToFirstSignificantSubdomain
 {
     static size_t getReserveLengthForElement() { return 15; }
@@ -18,7 +19,7 @@ struct CutToFirstSignificantSubdomain
         Pos tmp_data;
         size_t tmp_length;
         Pos domain_end;
-        ExtractFirstSignificantSubdomain::execute(data, size, tmp_data, tmp_length, &domain_end);
+        ExtractFirstSignificantSubdomain<without_www>::execute(data, size, tmp_data, tmp_length, &domain_end);
 
         if (tmp_length == 0)
             return;
@@ -29,11 +30,15 @@ struct CutToFirstSignificantSubdomain
 };
 
 struct NameCutToFirstSignificantSubdomain { static constexpr auto name = "cutToFirstSignificantSubdomain"; };
-using FunctionCutToFirstSignificantSubdomain = FunctionStringToString<ExtractSubstringImpl<CutToFirstSignificantSubdomain>, NameCutToFirstSignificantSubdomain>;
+using FunctionCutToFirstSignificantSubdomain = FunctionStringToString<ExtractSubstringImpl<CutToFirstSignificantSubdomain<true>>, NameCutToFirstSignificantSubdomain>;
+
+struct NameCutToFirstSignificantSubdomainWithWWW { static constexpr auto name = "cutToFirstSignificantSubdomainWithWWW"; };
+using FunctionCutToFirstSignificantSubdomainWithWWW = FunctionStringToString<ExtractSubstringImpl<CutToFirstSignificantSubdomain<false>>, NameCutToFirstSignificantSubdomainWithWWW>;
 
 void registerFunctionCutToFirstSignificantSubdomain(FunctionFactory & factory)
 {
     factory.registerFunction<FunctionCutToFirstSignificantSubdomain>();
+    factory.registerFunction<FunctionCutToFirstSignificantSubdomainWithWWW>();
 }
 
 }

src/Functions/URL/firstSignificantSubdomain.cpp

@@ -7,7 +7,7 @@ namespace DB
 {
 
 struct NameFirstSignificantSubdomain { static constexpr auto name = "firstSignificantSubdomain"; };
-using FunctionFirstSignificantSubdomain = FunctionStringToString<ExtractSubstringImpl<ExtractFirstSignificantSubdomain>, NameFirstSignificantSubdomain>;
+using FunctionFirstSignificantSubdomain = FunctionStringToString<ExtractSubstringImpl<ExtractFirstSignificantSubdomain<true>>, NameFirstSignificantSubdomain>;
 
 void registerFunctionFirstSignificantSubdomain(FunctionFactory & factory)
 {

src/Functions/URL/firstSignificantSubdomain.h

@@ -7,6 +7,7 @@
 namespace DB
 {
 
+template <bool without_www>
 struct ExtractFirstSignificantSubdomain
 {
     static size_t getReserveLengthForElement() { return 10; }
@@ -18,7 +19,7 @@ struct ExtractFirstSignificantSubdomain
 
         Pos tmp;
         size_t domain_length;
-        ExtractDomain<true>::execute(data, size, tmp, domain_length);
+        ExtractDomain<without_www>::execute(data, size, tmp, domain_length);
 
         if (domain_length == 0)
             return;

tests/queries/0_stateless/00398_url_functions.reference

@@ -78,6 +78,15 @@ example.com
 example.com
 example.com
 example.com
+com
+
+====CUT TO FIRST SIGNIFICANT SUBDOMAIN WITH WWW====
+
+www.com
+example.com
+example.com
+example.com
+example.com
 ====CUT WWW====
 http://example.com
 http://example.com:1234

tests/queries/0_stateless/00398_url_functions.sql

@@ -86,6 +86,16 @@ SELECT cutToFirstSignificantSubdomain('http://paul@www.example.com/a/b/c?a=b#d=f
 SELECT cutToFirstSignificantSubdomain('//paul@www.example.com/a/b/c?a=b#d=f');
 SELECT cutToFirstSignificantSubdomain('www.example.com');
 SELECT cutToFirstSignificantSubdomain('example.com');
+SELECT cutToFirstSignificantSubdomain('www.com');
+SELECT cutToFirstSignificantSubdomain('com');
+
+SELECT '====CUT TO FIRST SIGNIFICANT SUBDOMAIN WITH WWW====';
+SELECT cutToFirstSignificantSubdomainWithWWW('http://com');
+SELECT cutToFirstSignificantSubdomainWithWWW('http://www.com');
+SELECT cutToFirstSignificantSubdomainWithWWW('http://www.example.com');
+SELECT cutToFirstSignificantSubdomainWithWWW('http://www.foo.example.com');
+SELECT cutToFirstSignificantSubdomainWithWWW('http://www.example.com:1');
+SELECT cutToFirstSignificantSubdomainWithWWW('http://www.example.com/');
 
 SELECT '====CUT WWW====';
 SELECT cutWWW('http://www.example.com');