Skip to content
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

optimized textwidth(::Char) for ASCII #55398

Merged
merged 9 commits into from
Aug 7, 2024
Merged

optimized textwidth(::Char) for ASCII #55398

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5d64115
optimized textwidth(::Char) for ASCII
stevengj Aug 6, 2024
16b269f
fix AbstractChar vs Char
stevengj Aug 6, 2024
68d372c
more textwidth tests
stevengj Aug 6, 2024
516bfd4
tuple table is faster
stevengj Aug 6, 2024
c67ebbe
replace lookup table with check
stevengj Aug 6, 2024
dcad1b0
more tests
stevengj Aug 6, 2024
a5cdf25
Update base/strings/unicode.jl
stevengj Aug 7, 2024
024e83d
Update base/strings/unicode.jl
stevengj Aug 7, 2024
8af04ee
Merge branch 'master' into ascii_textwidth
stevengj Aug 7, 2024
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
9 changes: 9 additions & 0 deletions base/strings/unicode.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,6 +256,15 @@ julia> textwidth('⛵')
```
"""
function textwidth(c::AbstractChar)
ismalformed(c) && return 1
i = codepoint(c)
i < 0x7f && return Int(i >= 0x20) # ASCII fast path
Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), i))
end

function textwidth(c::Char)
b = bswap(reinterpret(UInt32, c)) # from isascii(c)
b < 0x7f && return Int(b >= 0x20) # ASCII fast path
ismalformed(c) && return 1
Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), c))
end
Expand Down
14 changes: 14 additions & 0 deletions test/strings/util.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,20 @@

SubStr(s) = SubString("abc$(s)de", firstindex(s) + 3, lastindex(s) + 3)

@testset "textwidth" begin
for (c, w) in [('x', 1), ('α', 1), ('🍕', 2), ('\0', 0), ('\u0302', 0), ('\xc0', 1)]
@test textwidth(c) == w
@test textwidth(c^3) == w*3
@test w == @invoke textwidth(c::AbstractChar)
end
for i in 0x00:0x7f # test all ASCII chars (which have fast path)
w = Int(ccall(:utf8proc_charwidth, Cint, (UInt32,), i))
c = Char(i)
@test textwidth(c) == w
@test w == @invoke textwidth(c::AbstractChar)
end
end

@testset "padding (lpad and rpad)" begin
@test lpad("foo", 2) == "foo"
@test rpad("foo", 2) == "foo"
Expand Down