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

Fix #11460, Fix #11464 uppercase/lowercase/map on a UTF16String should return a UTF16String #11735

Merged
merged 2 commits into from
Jun 24, 2015
Merged

Fix #11460, Fix #11464 uppercase/lowercase/map on a UTF16String should return a UTF16String #11735

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7e84bcf
Fix #11460, Fix #11464 UTF16String uppercase/lowercase/map
ScottPJones Jun 22, 2015
3e591e0
Added new tests for full coverage
ScottPJones Jun 19, 2015
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
25 changes: 25 additions & 0 deletions base/utf16.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,3 +143,28 @@ function utf16(p::Union{Ptr{UInt16}, Ptr{Int16}})
while unsafe_load(p, len+1) != 0; len += 1; end
utf16(p, len)
end

function map(fun, str::UTF16String)
buf = UInt16[]
sizehint!(buf, length(str.data))
for ch in str
c2 = fun(ch)
if !isa(c2, Char)
throw(UnicodeError(UTF_ERR_MAP_CHAR, 0, 0))
end
uc = reinterpret(UInt32, c2)
if uc < 0x10000
if utf16_is_surrogate(UInt16(uc))
throw(UnicodeError(UTF_ERR_INVALID_CHAR, 0, uc))
end
push!(buf, UInt16(uc))
elseif uc <= 0x10ffff
push!(buf, UInt16(0xd7c0 + (uc >> 10)))
push!(buf, UInt16(0xdc00 + (uc & 0x3ff)))
else
throw(UnicodeError(UTF_ERR_INVALID_CHAR, 0, uc))
end
end
push!(buf, 0)
UTF16String(buf)
end
20 changes: 20 additions & 0 deletions test/strings.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1897,3 +1897,23 @@ end
@test [c for c in "ḟøøƀäṙ"] == ['ḟ', 'ø', 'ø', 'ƀ', 'ä', 'ṙ']
@test [i for i in eachindex("ḟøøƀäṙ")] == [1, 4, 6, 8, 10, 12]
@test [x for x in enumerate("ḟøøƀäṙ")] == [(1, 'ḟ'), (2, 'ø'), (3, 'ø'), (4, 'ƀ'), (5, 'ä'), (6, 'ṙ')]

# issue # 11464: uppercase/lowercase of UTF16String becomes a UTF8String
str = "abcdef\uff\uffff\u10ffffABCDEF"
@test typeof(uppercase("abcdef")) == ASCIIString
@test typeof(uppercase(utf8(str))) == UTF8String
@test typeof(uppercase(utf16(str))) == UTF16String
@test typeof(uppercase(utf32(str))) == UTF32String
@test typeof(lowercase("ABCDEF")) == ASCIIString
@test typeof(lowercase(utf8(str))) == UTF8String
@test typeof(lowercase(utf16(str))) == UTF16String
@test typeof(lowercase(utf32(str))) == UTF32String

foomap(ch) = (ch > 65)
foobar(ch) = Char(0xd800)
foobaz(ch) = Char(0x200000)
@test_throws UnicodeError map(foomap, utf16(str))
@test_throws UnicodeError map(foobar, utf16(str))
@test_throws UnicodeError map(foobaz, utf16(str))