Skip to content

Optimize ISO datetime parsing using binary pattern matching with nibbles #14177

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

Closed
wants to merge 3 commits into from
Closed

Optimize ISO datetime parsing using binary pattern matching with nibbles #14177

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
61a0460
Optimize ISO datetime parsing using binary pattern matching with nibbles
dkuku Jan 11, 2025
f8842ef
ascii macro
dkuku Jan 22, 2025
ab95462
rename to int
dkuku Jan 22, 2025
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
67 changes: 40 additions & 27 deletions lib/elixir/lib/calendar/iso.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,11 @@
defmodule Ascii do
defmacro int(x) do
quote do
<<3::4, unquote(x)::4>>
end
end
end

defmodule Calendar.ISO do
@moduledoc """
The default calendar implementation, a Gregorian calendar following ISO 8601.
Expand Down Expand Up @@ -200,33 +208,34 @@ defmodule Calendar.ISO do
# on ~D[0001-01-01] which is 366 days later.
@iso_epoch 366

import Ascii

[match_basic_date, match_ext_date, guard_date, read_date] =
quote do
[
<<y1, y2, y3, y4, m1, m2, d1, d2>>,
<<y1, y2, y3, y4, @ext_date_sep, m1, m2, @ext_date_sep, d1, d2>>,
y1 >= ?0 and y1 <= ?9 and y2 >= ?0 and y2 <= ?9 and y3 >= ?0 and y3 <= ?9 and y4 >= ?0 and
y4 <= ?9 and m1 >= ?0 and m1 <= ?9 and m2 >= ?0 and m2 <= ?9 and d1 >= ?0 and d1 <= ?9 and
d2 >= ?0 and d2 <= ?9,
<<int(y1), int(y2), int(y3), int(y4), int(m1), int(m2), int(d1), int(d2)>>,
<<int(y1), int(y2), int(y3), int(y4), @ext_date_sep, int(m1), int(m2), @ext_date_sep,
int(d1), int(d2)>>,
y1 <= 9 and y2 <= 9 and y3 <= 9 and y4 <= 9 and m1 <= 9 and m2 <= 9 and d1 <= 9 and
d2 <= 9,
{
(y1 - ?0) * 1000 + (y2 - ?0) * 100 + (y3 - ?0) * 10 + (y4 - ?0),
(m1 - ?0) * 10 + (m2 - ?0),
(d1 - ?0) * 10 + (d2 - ?0)
y1 * 1000 + y2 * 100 + y3 * 10 + y4,
m1 * 10 + m2,
d1 * 10 + d2
}
]
end

[match_basic_time, match_ext_time, guard_time, read_time] =
quote do
[
<<h1, h2, i1, i2, s1, s2>>,
<<h1, h2, @ext_time_sep, i1, i2, @ext_time_sep, s1, s2>>,
h1 >= ?0 and h1 <= ?9 and h2 >= ?0 and h2 <= ?9 and i1 >= ?0 and i1 <= ?9 and i2 >= ?0 and
i2 <= ?9 and s1 >= ?0 and s1 <= ?9 and s2 >= ?0 and s2 <= ?9,
<<int(h1), int(h2), int(i1), int(i2), int(s1), int(s2)>>,
<<int(h1), int(h2), @ext_time_sep, int(i1), int(i2), @ext_time_sep, int(s1), int(s2)>>,
h1 <= 9 and h2 <= 9 and i1 <= 9 and i2 <= 9 and s1 <= 9 and s2 <= 9,
{
(h1 - ?0) * 10 + (h2 - ?0),
(i1 - ?0) * 10 + (i2 - ?0),
(s1 - ?0) * 10 + (s2 - ?0)
h1 * 10 + h2,
i1 * 10 + i2,
s1 * 10 + s2
}
]
end
Expand Down Expand Up @@ -2021,34 +2030,38 @@ defmodule Calendar.ISO do
defp parse_offset("Z"), do: {0, ""}
defp parse_offset("-00:00"), do: :error

defp parse_offset(<<?+, h1, h2, ?:, m1, m2, rest::binary>>),
defp parse_offset(<<?+, int(h1), int(h2), ?:, int(m1), int(m2), rest::binary>>),
do: parse_offset(1, h1, h2, m1, m2, rest)

defp parse_offset(<<?-, h1, h2, ?:, m1, m2, rest::binary>>),
defp parse_offset(<<?-, int(h1), int(h2), ?:, int(m1), int(m2), rest::binary>>),
do: parse_offset(-1, h1, h2, m1, m2, rest)

defp parse_offset(<<?+, h1, h2, m1, m2, rest::binary>>),
defp parse_offset(<<?+, int(h1), int(h2), int(m1), int(m2), rest::binary>>),
do: parse_offset(1, h1, h2, m1, m2, rest)

defp parse_offset(<<?-, h1, h2, m1, m2, rest::binary>>),
defp parse_offset(<<?-, int(h1), int(h2), int(m1), int(m2), rest::binary>>),
do: parse_offset(-1, h1, h2, m1, m2, rest)

defp parse_offset(<<?+, h1, h2, rest::binary>>), do: parse_offset(1, h1, h2, ?0, ?0, rest)
defp parse_offset(<<?-, h1, h2, rest::binary>>), do: parse_offset(-1, h1, h2, ?0, ?0, rest)
defp parse_offset(<<?+, int(h1), int(h2), rest::binary>>),
do: parse_offset(1, h1, h2, 0, 0, rest)

defp parse_offset(<<?-, int(h1), int(h2), rest::binary>>),
do: parse_offset(-1, h1, h2, 0, 0, rest)

defp parse_offset(_), do: :error

defp parse_offset(sign, h1, h2, m1, m2, rest) do
with true <- h1 in ?0..?2 and h2 in ?0..?9,
true <- m1 in ?0..?5 and m2 in ?0..?9,
hour = (h1 - ?0) * 10 + h2 - ?0,
min = (m1 - ?0) * 10 + m2 - ?0,
true <- hour < 24 do
defp parse_offset(sign, h1, h2, m1, m2, rest)
when h2 < 10 and m1 < 6 and m2 < 10 do
with hour when hour < 24 <- h1 * 10 + h2,
min = m1 * 10 + m2 do
{(hour * 60 + min) * 60 * sign, rest}
else
_ -> :error
end
end

defp parse_offset(_, _, _, _, _, _), do: :error

@doc false
def gregorian_seconds_to_iso_days(seconds, microsecond) do
{days, rest_seconds} = div_rem(seconds, @seconds_per_day)
Expand Down