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.

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

Make String(::Memory) copy #54457

Merged
merged 16 commits into from
Oct 25, 2024
Merged
Show file tree
Hide file tree
Changes from 10 commits
Commits
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
2 changes: 1 addition & 1 deletion base/gmp.jl
Original file line number Diff line number Diff line change
Expand Up @@ -761,7 +761,7 @@ function string(n::BigInt; base::Integer = 10, pad::Integer = 1)
sv[i] = '0' % UInt8
end
isneg(n) && (sv[1] = '-' % UInt8)
String(sv)
Base._unsafe_takestring!(sv)
end

function digits!(a::AbstractVector{T}, n::BigInt; base::Integer = 10) where {T<:Integer}
Expand Down
12 changes: 6 additions & 6 deletions base/intfuncs.jl
Original file line number Diff line number Diff line change
Expand Up @@ -766,7 +766,7 @@ function bin(x::Unsigned, pad::Int, neg::Bool)
i -= 1
end
neg && (@inbounds a[1] = 0x2d) # UInt8('-')
String(a)
_unsafe_takestring!(a)
end

function oct(x::Unsigned, pad::Int, neg::Bool)
Expand All @@ -780,7 +780,7 @@ function oct(x::Unsigned, pad::Int, neg::Bool)
i -= 1
end
neg && (@inbounds a[1] = 0x2d) # UInt8('-')
String(a)
_unsafe_takestring!(a)
end

# 2-digit decimal characters ("00":"99")
Expand Down Expand Up @@ -850,7 +850,7 @@ function dec(x::Unsigned, pad::Int, neg::Bool)
a = StringMemory(n)
append_c_digits_fast(n, x, a, 1)
neg && (@inbounds a[1] = 0x2d) # UInt8('-')
String(a)
_unsafe_takestring!(a)
end

function hex(x::Unsigned, pad::Int, neg::Bool)
Expand All @@ -871,7 +871,7 @@ function hex(x::Unsigned, pad::Int, neg::Bool)
@inbounds a[i] = d + ifelse(d > 0x9, 0x57, 0x30)
end
neg && (@inbounds a[1] = 0x2d) # UInt8('-')
String(a)
_unsafe_takestring!(a)
end

const base36digits = UInt8['0':'9';'a':'z']
Expand All @@ -896,7 +896,7 @@ function _base(base::Integer, x::Integer, pad::Int, neg::Bool)
i -= 1
end
neg && (@inbounds a[1] = 0x2d) # UInt8('-')
String(a)
_unsafe_takestring!(a)
end

split_sign(n::Integer) = unsigned(abs(n)), n < 0
Expand Down Expand Up @@ -972,7 +972,7 @@ function bitstring(x::T) where {T}
x = lshr_int(x, 4)
i -= 4
end
return String(str)
return _unsafe_takestring!(str)
end

"""
Expand Down
19 changes: 13 additions & 6 deletions base/strings/string.jl
Original file line number Diff line number Diff line change
Expand Up @@ -61,12 +61,7 @@ by [`take!`](@ref) on a writable [`IOBuffer`](@ref) and by calls to
In other cases, `Vector{UInt8}` data may be copied, but `v` is truncated anyway
to guarantee consistent behavior.
"""
String(v::AbstractVector{UInt8}) = String(copyto!(StringMemory(length(v)), v))
function String(v::Memory{UInt8})
len = length(v)
len == 0 && return ""
return ccall(:jl_genericmemory_to_string, Ref{String}, (Any, Int), v, len)
end
String(v::AbstractVector{UInt8}) = _unsafe_takestring!(copyto!(StringMemory(length(v)), v))
function String(v::Vector{UInt8})
#return ccall(:jl_array_to_string, Ref{String}, (Any,), v)
len = length(v)
Expand All @@ -83,6 +78,18 @@ function String(v::Vector{UInt8})
return str
end

"""
_unsafe_takestring!(v::Memory{UInt8})

Create a new `String` object using the data buffer from byte vector `v`, and leaves `v` in an inconsistent state. This should only be used internally for performance-critical
`String` routines that immediately discard `v` afterwards.
"""
function _unsafe_takestring!(v::Memory{UInt8})
len = length(v)
len == 0 && return ""
return ccall(:jl_genericmemory_to_string, Ref{String}, (Any, Int), v, len)
end

"""
unsafe_string(p::Ptr{UInt8}, [length::Integer])

Expand Down
2 changes: 1 addition & 1 deletion base/strings/util.jl
Original file line number Diff line number Diff line change
Expand Up @@ -1214,7 +1214,7 @@ function bytes2hex(itr)
b[2i - 1] = hex_chars[1 + x >> 4]
b[2i ] = hex_chars[1 + x & 0xf]
end
return String(b)
return Base._unsafe_takestring!(b)
end

function bytes2hex(io::IO, itr)
Expand Down
2 changes: 1 addition & 1 deletion base/uuid.jl
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ let groupings = [36:-1:25; 23:-1:20; 18:-1:15; 13:-1:10; 8:-1:1]
u >>= 4
end
@inbounds a[24] = a[19] = a[14] = a[9] = '-'
return String(a)
return Base._unsafe_takestring!(a)
end
end

Expand Down
2 changes: 1 addition & 1 deletion stdlib/FileWatching/src/pidfile.jl
Original file line number Diff line number Diff line change
Expand Up @@ -280,7 +280,7 @@ function open_exclusive(path::String;
end

function _rand_filename(len::Int=4) # modified from Base.Libc
slug = Base.StringMemory(len)
slug = Base.StringVector(len)
nhz2 marked this conversation as resolved.
Show resolved Hide resolved
chars = b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
for i = 1:len
slug[i] = chars[(Libc.rand() % length(chars)) + 1]
Expand Down
11 changes: 11 additions & 0 deletions test/strings/basic.jl
Original file line number Diff line number Diff line change
Expand Up @@ -1093,6 +1093,17 @@ let v = [0x40,0x41,0x42]
@test String(view(v, 2:3)) == "AB"
end

# issue #54369
let v = Base.StringMemory(3)
v .= [0x41,0x42,0x43]
s = String(v)
@test s == "ABC"
@test v == [0x41,0x42,0x43]
v[1] = 0x43
@test s == "ABC"
@test v == [0x43,0x42,0x43]
end

# make sure length for identical String and AbstractString return the same value, PR #25533
let rng = MersenneTwister(1), strs = ["∀εa∀aε"*String(rand(rng, UInt8, 100))*"∀εa∀aε",
String(rand(rng, UInt8, 200))]
Expand Down