thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 08:32:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add a way to accept URL without scheme for domain and topLevelDomain

Browse Source
This commit is contained in:
Guillaume Tassery 2019-04-16 11:57:46 +07:00
parent cdc65eca23
commit 6df315a985
3 changed files with 21 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
dbms/src/Functions/domain.h
View File

@ -9,27 +9,31 @@ namespace DB
{
/// Extracts host from given url.
template <bool ignore_scheme = true>
inline StringRef getURLHost(const char * data, size_t size)
{
Pos pos = data;
Pos end = data + size;
if (end == (pos = find_first_symbols<'/'>(pos, end)))
return {};
if (pos != data)
if (!ignore_scheme || strncmp("www.", data, 4))
{
StringRef scheme = getURLScheme(data, size);
Pos scheme_end = data + scheme.size;
// Colon must follows after scheme.
if (pos - scheme_end != 1 || *scheme_end != ':')
if (end == (pos = find_first_symbols<'/'>(pos, end)))
return {};
}
if (end - pos < 2 || *(pos) != '/' || *(pos + 1) != '/')
return {};
pos += 2;
if (pos != data)
{
StringRef scheme = getURLScheme(data, size);
Pos scheme_end = data + scheme.size;
// Colon must follows after scheme.
if (pos - scheme_end != 1 || *scheme_end != ':')
return {};
}
if (end - pos < 2 || *(pos) != '/' || *(pos + 1) != '/')
return {};
pos += 2;
}
const char * start_of_host = pos;
for (; pos < end; ++pos)

2
dbms/tests/queries/0_stateless/00398_url_functions.reference
View File

@ -12,6 +12,7 @@ www.example.com
127.0.0.1
www.example.com
www.example.com
www.example.com
example.com
example.com
====DOMAIN====
@ -20,6 +21,7 @@ com
ru
ru
com
com
====PATH====
П
%D%9

2
dbms/tests/queries/0_stateless/00398_url_functions.sql
View File

@ -13,6 +13,7 @@ SELECT domain('http://www.example.com?q=4') AS Host;
SELECT domain('http://127.0.0.1:443/') AS Host;
SELECT domain('//www.example.com') AS Host;
SELECT domain('//paul@www.example.com') AS Host;
SELECT domain('www.example.com') as Host;
SELECT domainWithoutWWW('//paul@www.example.com') AS Host;
SELECT domainWithoutWWW('http://paul@www.example.com:80/') AS Host;
@ -23,6 +24,7 @@ SELECT topLevelDomain('http://127.0.0.1:443/') AS Domain;
SELECT topLevelDomain('svn+ssh://example.ru?q=hello%20world') AS Domain;
SELECT topLevelDomain('svn+ssh://example.ru.?q=hello%20world') AS Domain;
SELECT topLevelDomain('//www.example.com') AS Domain;
SELECT topLevelDomain('www.google.com') as Domain;
SELECT '====PATH====';
SELECT decodeURLComponent('%D0%9F');