Skip to content

PERF: Cython version of Python _TIMEPAT regexp in parsing.pyx #26204

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Apr 24, 2019
Merged

PERF: Cython version of Python _TIMEPAT regexp in parsing.pyx #26204

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9a12c7e
Replace regexp-based checking for string being time with Cython impl
vnlitvinov Feb 5, 2019
98c0556
added test case for benchmarking does_string_look_like_time; added in…
anmyachev Apr 2, 2019
464380f
Add docstring for does_string_look_like_time
vnlitvinov Apr 24, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions asv_bench/benchmarks/io/csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -252,11 +252,12 @@ def mem_parser_chunks(self):


class ReadCSVParseSpecialDate(StringIORewind):
params = (['mY', 'mdY'],)
params = (['mY', 'mdY', 'hm'],)
params_name = ['value']
objects = {
'mY': '01-2019\n10-2019\n02/2000\n',
'mdY': '12/02/2010\n'
'mdY': '12/02/2010\n',
'hm': '21:34\n'
}

def setup(self, value):
Expand Down
36 changes: 33 additions & 3 deletions pandas/_libs/tslibs/parsing.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,6 @@ _DEFAULT_DATETIME = datetime(1, 1, 1).replace(hour=0, minute=0,
second=0, microsecond=0)

cdef:
object _TIMEPAT = re.compile(r'^([01]?[0-9]|2[0-3]):([0-5][0-9])')

set _not_datelike_strings = {'a', 'A', 'm', 'M', 'p', 'P', 't', 'T'}

# ----------------------------------------------------------------------
Expand Down Expand Up @@ -144,6 +142,38 @@ cdef inline object _parse_delimited_date(object date_string, bint dayfirst):
raise DateParseError("Invalid date specified ({}/{})".format(month, day))


cdef inline bint does_string_look_like_time(object parse_string):
"""
Checks whether given string is a time: it has to start either from
H:MM or from HH:MM, and hour and minute values must be valid.

Parameters
----------
date_string : str

Returns:
--------
whether given string is a time
"""
cdef:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you add a doc-string here

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

docstring added

const char* buf
Py_ssize_t length
int hour = -1, minute = -1

buf = get_c_string_buf_and_size(parse_string, &length)
if length >= 4:
if buf[1] == b':':
# h:MM format
hour = getdigit_ascii(buf[0], -1)
minute = _parse_2digit(buf + 2)
elif buf[2] == b':':
# HH:MM format
hour = _parse_2digit(buf)
minute = _parse_2digit(buf + 3)

return 0 <= hour <= 23 and 0 <= minute <= 59


def parse_datetime_string(date_string, freq=None, dayfirst=False,
yearfirst=False, **kwargs):
"""parse datetime string, only returns datetime.
Expand All @@ -160,7 +190,7 @@ def parse_datetime_string(date_string, freq=None, dayfirst=False,
if not _does_string_look_like_datetime(date_string):
raise ValueError('Given date string not likely a datetime.')

if _TIMEPAT.match(date_string):
if does_string_look_like_time(date_string):
# use current datetime as default, not pass _DEFAULT_DATETIME
dt = du_parse(date_string, dayfirst=dayfirst,
yearfirst=yearfirst, **kwargs)
Expand Down