mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-09-20 08:40:50 +00:00
Added more formats to "parseDateTimeBestEffort" function [#CLICKHOUSE-2]
This commit is contained in:
Alexey Milovidov
parent
14e425ddb4
commit
66a0c1691d
@ -86,6 +86,25 @@ ReturnType parseDateTimeBestEffortImpl(time_t & res, ReadBuffer & in, const Date
|
||||
|
||||
bool is_pm = false;
|
||||
|
||||
auto read_alpha_month = [&month] (const auto & alpha)
|
||||
{
|
||||
if (0 == strncasecmp(alpha, "Jan", 3)) month = 1;
|
||||
else if (0 == strncasecmp(alpha, "Feb", 3)) month = 2;
|
||||
else if (0 == strncasecmp(alpha, "Mar", 3)) month = 3;
|
||||
else if (0 == strncasecmp(alpha, "Apr", 3)) month = 4;
|
||||
else if (0 == strncasecmp(alpha, "May", 3)) month = 5;
|
||||
else if (0 == strncasecmp(alpha, "Jun", 3)) month = 6;
|
||||
else if (0 == strncasecmp(alpha, "Jul", 3)) month = 7;
|
||||
else if (0 == strncasecmp(alpha, "Aug", 3)) month = 8;
|
||||
else if (0 == strncasecmp(alpha, "Sep", 3)) month = 9;
|
||||
else if (0 == strncasecmp(alpha, "Oct", 3)) month = 10;
|
||||
else if (0 == strncasecmp(alpha, "Nov", 3)) month = 11;
|
||||
else if (0 == strncasecmp(alpha, "Dec", 3)) month = 12;
|
||||
else
|
||||
return false;
|
||||
return true;
|
||||
};
|
||||
|
||||
while (!in.eof())
|
||||
{
|
||||
char digits[14];
|
||||
@ -205,6 +224,10 @@ ReturnType parseDateTimeBestEffortImpl(time_t & res, ReadBuffer & in, const Date
|
||||
/// hh - only if already have day of month
|
||||
/// DD/MM/YYYY
|
||||
/// DD/MM/YY
|
||||
/// DD.MM.YYYY
|
||||
/// DD.MM.YY
|
||||
/// DD-MM-YYYY
|
||||
/// DD-MM-YY
|
||||
/// DD
|
||||
|
||||
UInt8 hour_or_day_of_month = 0;
|
||||
@ -244,7 +267,7 @@ ReturnType parseDateTimeBestEffortImpl(time_t & res, ReadBuffer & in, const Date
|
||||
return on_error("Cannot read DateTime: unexpected number of decimal digits after hour and minute: " + toString(num_digits), ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
}
|
||||
}
|
||||
else if (checkChar('/', in))
|
||||
else if (checkChar('/', in) || checkChar('.', in) || checkChar('-', in))
|
||||
{
|
||||
if (day_of_month)
|
||||
return on_error("Cannot read DateTime: day of month is duplicated", ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
@ -260,10 +283,23 @@ ReturnType parseDateTimeBestEffortImpl(time_t & res, ReadBuffer & in, const Date
|
||||
readDecimalNumber<2>(month, digits);
|
||||
else if (num_digits == 1)
|
||||
readDecimalNumber<1>(month, digits);
|
||||
else if (num_digits == 0)
|
||||
{
|
||||
/// Month in alphabetical form
|
||||
|
||||
char alpha[9]; /// The longest month name: September
|
||||
size_t num_alpha = readAlpha(alpha, sizeof(alpha), in);
|
||||
|
||||
if (num_alpha < 3)
|
||||
return on_error("Cannot read DateTime: unexpected number of alphabetical characters after day of month: " + toString(num_alpha), ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
|
||||
if (!read_alpha_month(alpha))
|
||||
return on_error("Cannot read DateTime: alphabetical characters after day of month don't look like month: " + std::string(alpha, 3), ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
}
|
||||
else
|
||||
return on_error("Cannot read DateTime: unexpected number of decimal digits after day of month: " + toString(num_digits), ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
|
||||
if (checkChar('/', in))
|
||||
if (checkChar('/', in) || checkChar('.', in) || checkChar('-', in))
|
||||
{
|
||||
if (year)
|
||||
return on_error("Cannot read DateTime: year component is duplicated", ErrorCodes::CANNOT_PARSE_DATETIME);
|
||||
@ -401,19 +437,9 @@ ReturnType parseDateTimeBestEffortImpl(time_t & res, ReadBuffer & in, const Date
|
||||
{
|
||||
bool has_day_of_week = false;
|
||||
|
||||
if (0 == strncasecmp(alpha, "Jan", 3)) month = 1;
|
||||
else if (0 == strncasecmp(alpha, "Feb", 3)) month = 2;
|
||||
else if (0 == strncasecmp(alpha, "Mar", 3)) month = 3;
|
||||
else if (0 == strncasecmp(alpha, "Apr", 3)) month = 4;
|
||||
else if (0 == strncasecmp(alpha, "May", 3)) month = 5;
|
||||
else if (0 == strncasecmp(alpha, "Jun", 3)) month = 6;
|
||||
else if (0 == strncasecmp(alpha, "Jul", 3)) month = 7;
|
||||
else if (0 == strncasecmp(alpha, "Aug", 3)) month = 8;
|
||||
else if (0 == strncasecmp(alpha, "Sep", 3)) month = 9;
|
||||
else if (0 == strncasecmp(alpha, "Oct", 3)) month = 10;
|
||||
else if (0 == strncasecmp(alpha, "Nov", 3)) month = 11;
|
||||
else if (0 == strncasecmp(alpha, "Dec", 3)) month = 12;
|
||||
|
||||
if (read_alpha_month(alpha))
|
||||
{
|
||||
}
|
||||
else if (0 == strncasecmp(alpha, "UTC", 3)) has_time_zone_offset = true;
|
||||
else if (0 == strncasecmp(alpha, "GMT", 3)) has_time_zone_offset = true;
|
||||
else if (0 == strncasecmp(alpha, "MSK", 3)) { has_time_zone_offset = true; time_zone_offset_hour = 3; }
|
||||
|
||||
@ -34,7 +34,7 @@ class ReadBuffer;
|
||||
* YYYYMM - 6 digits is a year, month if year was not already read
|
||||
* hhmmss - 6 digits is a time if year was already read
|
||||
*
|
||||
* .nnnnnnn - any number of digits after point is fractional part of second, if it is not YYYY.MM.DD
|
||||
* .nnnnnnn - any number of digits after point is fractional part of second, if it is not YYYY.MM.DD or DD.MM.YYYY
|
||||
*
|
||||
* T - means that time will follow
|
||||
*
|
||||
|
||||
@ -0,0 +1,21 @@
|
||||
s a b
|
||||
|
||||
24.12.2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-12-2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24.12.18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-12-18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-Dec-18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24/DEC/18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24/DEC/2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
01-OCT-2015 2015-10-01 00:00:00 2015-10-01 00:00:00
|
||||
24.12.2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-12-2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24.12.18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-12-18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24-Dec-18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24/DEC/18 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
24/DEC/2018 2018-12-24 00:00:00 2018-12-24 00:00:00
|
||||
01-OCT-2015 2015-10-01 00:00:00 2015-10-01 00:00:00
|
||||
24.12.18 010203 2018-12-24 01:02:03 2018-12-24 01:02:03
|
||||
24.12.18 01:02:03 2018-12-24 01:02:03 2018-12-24 01:02:03
|
||||
24.DEC.18T01:02:03.000+0300 2018-12-23 22:02:03 2018-12-23 22:02:03
|
||||
@ -0,0 +1,28 @@
|
||||
SELECT
|
||||
s,
|
||||
parseDateTimeBestEffortOrNull(s, 'UTC') AS a,
|
||||
parseDateTimeBestEffortOrZero(s, 'UTC') AS b
|
||||
FROM
|
||||
(
|
||||
SELECT arrayJoin([
|
||||
'24.12.2018',
|
||||
'24-12-2018',
|
||||
'24.12.18',
|
||||
'24-12-18',
|
||||
'24-Dec-18',
|
||||
'24/DEC/18',
|
||||
'24/DEC/2018',
|
||||
'01-OCT-2015',
|
||||
'24.12.2018',
|
||||
'24-12-2018',
|
||||
'24.12.18',
|
||||
'24-12-18',
|
||||
'24-Dec-18',
|
||||
'24/DEC/18',
|
||||
'24/DEC/2018',
|
||||
'01-OCT-2015',
|
||||
'24.12.18 010203',
|
||||
'24.12.18 01:02:03',
|
||||
'24.DEC.18T01:02:03.000+0300'
|
||||
]) AS s)
|
||||
FORMAT PrettySpaceNoEscapes;
|
||||
Loading…
Reference in New Issue
Block a user