thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-23 08:02:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #53059 from ClibMouse/feature/hastokenornull-empty-needle

Browse Source 
Make hasTokenOrNull return null on empty needle
This commit is contained in:
Alexey Milovidov 2023-08-12 03:35:08 +03:00 committed by GitHub
commit ad82dcec7d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/Functions/HasTokenImpl.h
View File

@ -13,6 +13,7 @@ namespace ErrorCodes
extern const int BAD_ARGUMENTS;
extern const int ILLEGAL_COLUMN;
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
extern const int LOGICAL_ERROR;
}
/** Token search the string, means that needle must be surrounded by some separator chars, like whitespace or puctuation.
@ -39,9 +40,6 @@ struct HasTokenImpl
if (start_pos != nullptr)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Function '{}' does not support start_pos argument", name);
if (pattern.empty())
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Needle cannot be empty, because empty string isn't a token");
if (haystack_offsets.empty())
return;
@ -49,7 +47,7 @@ struct HasTokenImpl
const UInt8 * const end = haystack_data.data() + haystack_data.size();
const UInt8 * pos = begin;
if (!std::none_of(pattern.begin(), pattern.end(), isTokenSeparator))
if (const auto has_separator = std::any_of(pattern.cbegin(), pattern.cend(), isTokenSeparator); has_separator || pattern.empty())
{
if (res_null)
{
@ -57,8 +55,12 @@ struct HasTokenImpl
std::ranges::fill(res_null->getData(), true);
return;
}
else
else if (has_separator)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Needle must not contain whitespace or separator characters");
else if (pattern.empty())
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Needle cannot be empty, because empty string isn't a token");
else
throw Exception(ErrorCodes::LOGICAL_ERROR, "Unexpected internal state");
}
size_t pattern_size = pattern.size();

4
tests/queries/0_stateless/02816_has_token_empty.reference
View File

@ -1,2 +1,6 @@
0
\N
\N
0
\N
\N

4
tests/queries/0_stateless/02816_has_token_empty.sql
View File

@ -2,6 +2,10 @@ SELECT hasTokenCaseInsensitive('K(G', ''); -- { serverError BAD_ARGUMENTS }
SELECT hasTokenCaseInsensitive('Hello', ''); -- { serverError BAD_ARGUMENTS }
SELECT hasTokenCaseInsensitive('', ''); -- { serverError BAD_ARGUMENTS }
SELECT hasTokenCaseInsensitive('', 'Hello');
SELECT hasTokenCaseInsensitiveOrNull('Hello', '');
SELECT hasTokenCaseInsensitiveOrNull('', '');
SELECT hasToken('Hello', ''); -- { serverError BAD_ARGUMENTS }
SELECT hasToken('', 'Hello');
SELECT hasToken('', ''); -- { serverError BAD_ARGUMENTS }
SELECT hasTokenOrNull('', '');
SELECT hasTokenOrNull('Hello', '');