Don't make a copy when passing a SubString to match

Only try to accept SubString{<:ByteString}
Sacha0 · Jul 26, 2015 · 6aa853d · 6aa853d
1 parent 295bf63
commit 6aa853d
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 3 deletions.
diff --git a/base/regex.jl b/base/regex.jl
@@ -137,7 +137,7 @@ end
 
 call(r::Regex, s) = ismatch(r, s)
 
-function match(re::Regex, str::UTF8String, idx::Integer, add_opts::UInt32=UInt32(0))
+function match(re::Regex, str::Union{SubString{UTF8String}, UTF8String}, idx::Integer, add_opts::UInt32=UInt32(0))
  compile(re)
  opts = re.match_options | add_opts
  if !PCRE.exec(re.regex, str, idx-1, opts, re.match_data)
@@ -152,8 +152,10 @@ function match(re::Regex, str::UTF8String, idx::Integer, add_opts::UInt32=UInt32
  RegexMatch(mat, cap, ovec[1]+1, off, re)
 end
 
-match(re::Regex, str::Union{ByteString,SubString}, idx::Integer, add_opts::UInt32=UInt32(0)) =
- match(re, utf8(str), idx, add_opts)
+_utf8(str) = utf8(str)
+_utf8(str::SubString{ASCIIString}) = convert(SubString{UTF8String}, str)
+match{T<:ByteString}(re::Regex, str::Union{T,SubString{T}}, idx::Integer, add_opts::UInt32=UInt32(0)) =
+ match(re, _utf8(str), idx, add_opts)
 
 match(r::Regex, s::AbstractString) = match(r, s, start(s))
 match(r::Regex, s::AbstractString, i::Integer) =

diff --git a/base/unicode/utf8.jl b/base/unicode/utf8.jl
@@ -214,6 +214,8 @@ write(io::IO, s::UTF8String) = write(io, s.data)
 utf8(x) = convert(UTF8String, x)
 convert(::Type{UTF8String}, s::UTF8String) = s
 convert(::Type{UTF8String}, s::ASCIIString) = UTF8String(s.data)
+convert(::Type{SubString{UTF8String}}, s::SubString{ASCIIString}) =
+ SubString(utf8(s.string), s.offset+1, s.endof+s.offset)
 convert(::Type{UTF8String}, a::Array{UInt8,1}) = isvalid(UTF8String, a) ? UTF8String(a) : throw(UnicodeError(UTF_ERR_INVALID_8))
 function convert(::Type{UTF8String}, a::Array{UInt8,1}, invalids_as::AbstractString)
  l = length(a)