thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-25 17:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

use is_trivial to decide whether to fallback

Browse Source
This commit is contained in:
taiyang-li 2024-04-10 12:17:10 +08:00
parent 907dddff3e
commit b885e67bbf
2 changed files with 29 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/Functions/splitByChar.cpp
View File

@ -99,7 +99,8 @@ public:
return false;
}
pos = reinterpret_cast<Pos>(memchrSmallAllowOverflow15(pos, separator, end - pos));
// pos = reinterpret_cast<Pos>(memchrSmallAllowOverflow15(pos, separator, end - pos));
pos = reinterpret_cast<Pos>(memchr(pos, separator, end - pos));
if (pos)
{
token_end = pos;

43
src/Functions/splitByRegexp.cpp
View File

@ -167,21 +167,8 @@ public:
FunctionBasePtr buildImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & return_type) const override
{
bool fallback_to_split_by_char = false;
const ColumnConst * col = checkAndGetColumnConstStringOrFixedString(arguments[0].column.get());
if (!col)
throw Exception(
ErrorCodes::ILLEGAL_COLUMN,
"Illegal column {} of first argument of function {}. "
"Must be constant string.",
arguments[0].column->getName(),
getName());
String pattern = col->getValue<String>();
if (pattern.size() == 1 && regex_symbols.count(pattern[0]) == 0)
fallback_to_split_by_char = true;
if (fallback_to_split_by_char)
/// If the first argument is a trivial char, fallback splitByRegexp to splitByChar for better performance
if (couldFallbackToSplitByChar(arguments))
return FunctionFactory::instance().getImpl("splitByChar", context)->build(arguments);
else
return std::make_unique<FunctionToFunctionBaseAdaptor>(
@ -194,9 +181,33 @@ public:
}
private:
bool couldFallbackToSplitByChar(const ColumnsWithTypeAndName & arguments) const
{
const ColumnConst * col = checkAndGetColumnConstStringOrFixedString(arguments[0].column.get());
if (!col)
throw Exception(
ErrorCodes::ILLEGAL_COLUMN,
"Illegal column {} of first argument of function {}. "
"Must be constant string.",
arguments[0].column->getName(),
getName());
String pattern = col->getValue<String>();
if (pattern.size() == 1)
{
auto re = std::make_shared<OptimizedRegularExpression>(Regexps::createRegexp<false, false, false>(col->getValue<String>()));
std::string required_substring;
bool is_trivial;
bool required_substring_is_prefix;
re->getAnalyzeResult(required_substring, is_trivial, required_substring_is_prefix);
return is_trivial;
}
return false;
}
ContextPtr context;
FunctionPtr split_by_regexp;
inline static const std::unordered_set<char> regex_symbols = {'^', '$', '\\', '.', '*', '+', '?', '(', ')', '[', ']', '{', '}', '|'};
};
}