wip

base/char.jl

@@ -12,7 +12,7 @@ end
 function ismalformed(c::Char)
  u = reinterpret(UInt32, c)
  l1 = leading_ones(u) << 3
- t0 = trailing_zeros(u) & 24
+ t0 = trailing_zeros(u) & 56
  (l1 == 8) | (l1 + t0 > 32) |
  (((u & 0x00c0c0c0) ⊻ 0x00808080) >> t0 != 0)
 end
@@ -22,7 +22,7 @@ function convert(::Type{UInt32}, c::Char)
  u = reinterpret(UInt32, c)
  u < 0x80000000 && return reinterpret(UInt32, u >> 24)
  l1 = leading_ones(u)
- t0 = trailing_zeros(u) & 24
+ t0 = trailing_zeros(u) & 56
  (l1 == 1) | (8l1 + t0 > 32) |
  (((u & 0x00c0c0c0) ⊻ 0x00808080) >> t0 != 0) &&
  malformed_char(c)::Union{}

base/repl/REPLCompletions.jl

@@ -106,7 +106,7 @@ const sorted_keywords = [
  "primitive type", "quote", "return", "struct",
  "true", "try", "using", "while"]
 
-function complete_keyword(s::String)
+function complete_keyword(s::Union{String,SubString{String}})
  r = searchsorted(sorted_keywords, s)
  i = first(r)
  n = length(sorted_keywords)

base/strings/string.jl

@@ -120,6 +120,8 @@ end
 
 ## thisind, prevind and nextind ##
 
+# TODO: these need updating
+
 function thisind(s::String, i::Integer)
  j = Int(i)
  j < 1 && return 0
@@ -131,8 +133,6 @@ function thisind(s::String, i::Integer)
  j
 end
 
-# TODO: these need updating
-
 function prevind(s::String, i::Integer)
  j = Int(i)
  e = sizeof(s)
@@ -244,22 +244,22 @@ function next(s::String, i::Int)
 end
 
 @noinline function next_continued(s::String, i::Int, u::UInt32)
- z = sizeof(s)
+ z = ncodeunits(s)
  # first continuation byte
  (i += 1) > z && @goto ret
  @inbounds b = codeunit(s, i)
- (b & 0xc0 == 0x80) || @goto ret
+ b & 0xc0 == 0x80 || @goto ret
  u |= UInt32(b) << 16
  # second continuation byte
  ((i += 1) > z) | (u < 0xe0000000) && @goto ret
  @inbounds b = codeunit(s, i)
- (b & 0xc0 == 0x80) || @goto ret
+ b & 0xc0 == 0x80 || @goto ret
  u |= UInt32(b) << 8
  # third continuation byte
  ((i += 1) > z) | (u < 0xf0000000) && @goto ret
  @inbounds b = codeunit(s, i)
- (b & 0xc0 == 0x80) || @goto ret
- u |= UInt32(b)
+ b & 0xc0 == 0x80 || @goto ret
+ u |= UInt32(b); i += 1
 @label ret
  return reinterpret(Char, u), i
 end

test/strings/io.jl

@@ -172,8 +172,7 @@ myio = IOBuffer()
 join(myio, "", "", 1)
 @test isempty(take!(myio))
 
-@testset "unescape_chars" begin
- @test Base.unescape_chars("\\t","t") == "t"
+@testset "unescape_string ArgumentErrors" begin
  @test_throws ArgumentError unescape_string(IOBuffer(), string('\\',"xZ"))
  @test_throws ArgumentError unescape_string(IOBuffer(), string('\\',"777"))
 end

test/unicode/utf8.jl

@@ -1,19 +1,8 @@
 # This file is a part of Julia. License is MIT: https://julialang.org/license
 
-@testset "cesu8 input" begin
- let ch = 0x10000
- for hi = 0xd800:0xdbff
- for lo = 0xdc00:0xdfff
- @test String(Vector{UInt8}(String(Char[hi, lo]))) == string(Char(ch))
- ch += 1
- end
- end
- end
-end
-
 @testset "string indexing" begin
  let str = String(b"this is a test\xed\x80")
- @test next(str, 15) == ('\ufffd', 16)
+ @test next(str, 15) == (reinterpret(Char, 0xed800000), 17)
  @test_throws BoundsError getindex(str, 0:3)
  @test_throws BoundsError getindex(str, 17:18)
  @test_throws BoundsError getindex(str, 2:17)
@@ -36,12 +25,12 @@ end
  b"xyz\xf0\x80" => b"\xf0\x80zyx",
  b"xyz\xf0\x80\x80" => b"\xf0\x80\x80zyx",
  ]
- @test_broken reverse(String(s)) == String(r)
+ @test reverse(String(s)) == String(r)
  end
 end
 
 @testset "string convert" begin
  @test String(b"this is a test\xed\x80\x80") == "this is a test\ud000"
- ## Specifically check UTF-8 string whose lead byte is same as a surrogate
+ # Specifically check UTF-8 string whose lead byte is same as a surrogate
  @test String(b"\xed\x9f\xbf") == "\ud7ff"
 end