move case functions and char predicates back to Base (#25479)

fixes #25394
JuliaLang · Jan 13, 2018 · c5cd13e · c5cd13e
1 parent 4a50e64
commit c5cd13e
Show file tree

Hide file tree

Showing 55 changed files with 120 additions and 223 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -174,7 +174,7 @@ The steps required to add a new docstring are listed below:
 Examples written within docstrings can be used as testcases known as "doctests" by annotating code blocks with `jldoctest`.
 
     ```jldoctest
-    julia> Unicode.uppercase("Docstring test")
+    julia> uppercase("Docstring test")
     "DOCSTRING TEST"
     ```
 

diff --git a/NEWS.md b/NEWS.md
@@ -874,11 +874,11 @@ Deprecated or removed
   * The `sum_kbn` and `cumsum_kbn` functions have been moved to the
     [KahanSummation](https://github.com/JuliaMath/KahanSummation.jl) package ([#24869]).
 
-  * Unicode-related string functions have been moved to the new `Unicode` standard
-    library module ([#25021]). This applies to `normalize_string`, `graphemes`,
-    `is_assigned_char`, `textwidth`, `islower`, `isupper`, `isalpha`,
-    `isdigit`, `isxdigit`, `isnumber`, `isalnum`, `iscntrl`, `ispunct`, `isspace`,
-    `isprint`, `isgraph`, `lowercase`, `uppercase`, `titlecase`, `lcfirst` and `ucfirst`.
+  * `isnumber` has been renamed to `isnumeric` ([#25021]).
+
+  * `is_assigned_char` and `normalize_string` have been renamed to `isassigned` and
+    `normalize`, and moved to the new `Unicode` standard library module.
+    `graphemes` has also been moved to that module ([#25021]).
 
   * The functions `eigs` and `svds` have been moved to the `IterativeEigensolvers` standard
     library module ([#24714]).
@@ -887,10 +887,6 @@ Deprecated or removed
 
   * `@printf` and `@sprintf` have been moved to the `Printf` standard library ([#23929],[#25056]).
 
-  * `isnumber` has been deprecated in favor of `isnumeric`, `is_assigned_char`
-    in favor of `isassigned` and `normalize_string` in favor of `normalize`, all three
-    in the new `Unicode` standard library module ([#25021]).
-
   * The aliases `Complex32`, `Complex64` and `Complex128` have been deprecated in favor of `ComplexF16`,
     `ComplexF32` and `ComplexF64` respectively ([#24647]).
 

diff --git a/base/arrayshow.jl b/base/arrayshow.jl
@@ -166,7 +166,7 @@ function print_matrix(io::IO, X::AbstractVecOrMat,
     screenwidth -= length(pre) + length(post)
     presp = repeat(" ", length(pre))  # indent each row to match pre string
     postsp = ""
-    @assert Unicode.textwidth(hdots) == Unicode.textwidth(ddots)
+    @assert textwidth(hdots) == textwidth(ddots)
     sepsize = length(sep)
     rowsA, colsA = axes(X,1), axes(X,2)
     m, n = length(rowsA), length(colsA)

diff --git a/base/char.jl b/base/char.jl
@@ -127,7 +127,7 @@ function show(io::IO, c::Char)
             (u <<= 8) == 0 && break
         end
         write(io, 0x27)
-    elseif Unicode.isprint(c)
+    elseif isprint(c)
         write(io, 0x27, c, 0x27)
     else # unprintable, well-formed, non-overlong Unicode
         u = UInt32(c)

diff --git a/base/deprecated.jl b/base/deprecated.jl
@@ -2614,23 +2614,10 @@ end
 @deprecate_moved normalize_string "Unicode" true true
 @deprecate_moved graphemes "Unicode" true true
 @deprecate_moved is_assigned_char "Unicode" true true
-@deprecate_moved textwidth "Unicode" true true
-@deprecate_moved islower "Unicode" true true
-@deprecate_moved isupper "Unicode" true true
-@deprecate_moved isalpha "Unicode" true true
-@deprecate_moved isdigit "Unicode" true true
-@deprecate_moved isnumber "Unicode" true true
-@deprecate_moved isalnum "Unicode" true true
-@deprecate_moved iscntrl "Unicode" true true
-@deprecate_moved ispunct "Unicode" true true
-@deprecate_moved isspace "Unicode" true true
-@deprecate_moved isprint "Unicode" true true
-@deprecate_moved isgraph "Unicode" true true
-@deprecate_moved lowercase "Unicode" true true
-@deprecate_moved uppercase "Unicode" true true
-@deprecate_moved titlecase "Unicode" true true
-@deprecate_moved lcfirst "Unicode" true true
-@deprecate_moved ucfirst "Unicode" true true
+
+@deprecate isalnum(c::Char) isalpha(c) || isnumeric(c)
+@deprecate isgraph(c::Char) isprint(c) && !isspace(c)
+@deprecate isnumber(c::Char) isnumeric(c)
 
 # PR #24647
 @deprecate_binding Complex32  ComplexF16

diff --git a/base/dict.jl b/base/dict.jl
@@ -1,15 +1,15 @@
 # This file is a part of Julia. License is MIT: https://julialang.org/license
 
 function _truncate_at_width_or_chars(str, width, chars="", truncmark="…")
-    truncwidth = Unicode.textwidth(truncmark)
+    truncwidth = textwidth(truncmark)
     (width <= 0 || width < truncwidth) && return ""
 
     wid = truncidx = lastidx = 0
     idx = start(str)
     while !done(str, idx)
         lastidx = idx
         c, idx = next(str, idx)
-        wid += Unicode.textwidth(c)
+        wid += textwidth(c)
         wid >= width - truncwidth && truncidx == 0 && (truncidx = lastidx)
         (wid >= width || c in chars) && break
     end

diff --git a/base/docs/utils.jl b/base/docs/utils.jl
@@ -3,7 +3,6 @@
 # Text / HTML objects
 
 import Base: print, show, ==, hash
-using Base.Unicode
 
 export HTML, @html_str
 
@@ -222,8 +221,8 @@ function matchinds(needle, haystack; acronym = false)
     for (i, char) in enumerate(haystack)
         isempty(chars) && break
         while chars[1] == ' ' popfirst!(chars) end # skip spaces
-        if Unicode.lowercase(char) == Unicode.lowercase(chars[1]) &&
-           (!acronym || !Unicode.isalpha(lastc))
+        if lowercase(char) == lowercase(chars[1]) &&
+           (!acronym || !isalpha(lastc))
             push!(is, i)
             popfirst!(chars)
         end

diff --git a/base/exports.jl b/base/exports.jl
@@ -696,7 +696,19 @@ export
     hex2bytes,
     hex2bytes!,
     info,
+    isalpha,
     isascii,
+    iscntrl,
+    isdigit,
+    islower,
+    isnumeric,
+    isprint,
+    ispunct,
+    isspace,
+    isupper,
+    isxdigit,
+    lcfirst,
+    lowercase,
     isvalid,
     join,
     logging,
@@ -728,9 +740,13 @@ export
     string,
     strip,
     summary,
+    textwidth,
     thisind,
+    titlecase,
     transcode,
+    ucfirst,
     unescape_string,
+    uppercase,
     warn,
 
 # logging frontend

diff --git a/base/interactiveutil.jl b/base/interactiveutil.jl
@@ -51,7 +51,7 @@ function edit(path::AbstractString, line::Integer=0)
         cmd = line != 0 ? `$command $path -l $line` : `$command $path`
     elseif startswith(name, "subl") || startswith(name, "atom")
         cmd = line != 0 ? `$command $path:$line` : `$command $path`
-    elseif name == "code" || (Sys.iswindows() && Unicode.uppercase(name) == "CODE.EXE")
+    elseif name == "code" || (Sys.iswindows() && uppercase(name) == "CODE.EXE")
         cmd = line != 0 ? `$command -g $path:$line` : `$command -g $path`
     elseif startswith(name, "notepad++")
         cmd = line != 0 ? `$command $path -n$line` : `$command $path`

diff --git a/base/io.jl b/base/io.jl
@@ -924,8 +924,6 @@ characters from that character until the start of the next line are ignored.
 julia> buf = IOBuffer("    text")
 IOBuffer(data=UInt8[...], readable=true, writable=false, seekable=true, append=false, size=8, maxsize=Inf, ptr=1, mark=-1)
 
-julia> using Unicode
-
 julia> skipchars(buf, isspace)
 IOBuffer(data=UInt8[...], readable=true, writable=false, seekable=true, append=false, size=8, maxsize=Inf, ptr=5, mark=-1)
 

diff --git a/base/libuv.jl b/base/libuv.jl
@@ -20,10 +20,10 @@ function uv_sizeof_req(req)
 end
 
 for h in uv_handle_types
-@eval const $(Symbol("_sizeof_",Unicode.lowercase(string(h)))) = uv_sizeof_handle($h)
+@eval const $(Symbol("_sizeof_",lowercase(string(h)))) = uv_sizeof_handle($h)
 end
 for r in uv_req_types
-@eval const $(Symbol("_sizeof_",Unicode.lowercase(string(r)))) = uv_sizeof_req($r)
+@eval const $(Symbol("_sizeof_",lowercase(string(r)))) = uv_sizeof_req($r)
 end
 
 uv_handle_data(handle) = ccall(:jl_uv_handle_data,Ptr{Cvoid},(Ptr{Cvoid},),handle)

diff --git a/base/markdown/Markdown.jl b/base/markdown/Markdown.jl
@@ -7,7 +7,6 @@ module Markdown
 
 import Base: show, ==, with_output_color
 import Core: @doc_str
-using Base.Unicode: lowercase, ucfirst, isspace
 
 include(joinpath("parse", "config.jl"))
 include(joinpath("parse", "util.jl"))

diff --git a/base/mpfr.jl b/base/mpfr.jl
@@ -132,7 +132,7 @@ BigFloat(x::Union{Float16,Float32}) = BigFloat(Float64(x))
 BigFloat(x::Rational) = BigFloat(numerator(x)) / BigFloat(denominator(x))
 
 function tryparse(::Type{BigFloat}, s::AbstractString, base::Int=0)
-    !isempty(s) && Base.Unicode.isspace(s[end]) && return tryparse(BigFloat, rstrip(s), base)
+    !isempty(s) && isspace(s[end]) && return tryparse(BigFloat, rstrip(s), base)
     z = BigFloat()
     err = ccall((:mpfr_set_str, :libmpfr), Int32, (Ref{BigFloat}, Cstring, Int32, Int32), z, s, base, ROUNDING_MODE[])
     err == 0 ? z : nothing

diff --git a/base/operators.jl b/base/operators.jl
@@ -753,8 +753,6 @@ entered in the Julia REPL (and most editors, appropriately configured) by typing
 
 # Examples
 ```jldoctest
-julia> using Unicode
-
 julia> map(uppercase∘hex, 250:255)
 6-element Array{String,1}:
  "FA"

diff --git a/base/parse.jl b/base/parse.jl
@@ -53,7 +53,7 @@ end
 function parseint_preamble(signed::Bool, base::Int, s::AbstractString, startpos::Int, endpos::Int)
     c, i, j = parseint_next(s, startpos, endpos)
 
-    while Unicode.isspace(c)
+    while isspace(c)
         c, i, j = parseint_next(s,i,endpos)
     end
     (j == 0) && (return 0, 0, 0)
@@ -66,7 +66,7 @@ function parseint_preamble(signed::Bool, base::Int, s::AbstractString, startpos:
         end
     end
 
-    while Unicode.isspace(c)
+    while isspace(c)
         c, i, j = parseint_next(s,i,endpos)
     end
     (j == 0) && (return 0, 0, 0)
@@ -124,10 +124,10 @@ function tryparse_internal(::Type{T}, s::AbstractString, startpos::Int, endpos::
             return n
         end
         c, i = next(s,i)
-        Unicode.isspace(c) && break
+        isspace(c) && break
     end
     (T <: Signed) && (n *= sgn)
-    while !Unicode.isspace(c)
+    while !isspace(c)
         d::T = '0' <= c <= '9' ? c-'0'    :
         'A' <= c <= 'Z' ? c-'A'+10 :
             'a' <= c <= 'z' ? c-'a'+a  : base
@@ -148,7 +148,7 @@ function tryparse_internal(::Type{T}, s::AbstractString, startpos::Int, endpos::
     end
     while i <= endpos
         c, i = next(s,i)
-        if !Unicode.isspace(c)
+        if !isspace(c)
             raise && throw(ArgumentError("extra characters after whitespace in $(repr(SubString(s,startpos,endpos)))"))
             return nothing
         end
@@ -167,10 +167,10 @@ function tryparse_internal(::Type{Bool}, sbuff::Union{String,SubString{String}},
     orig_end   = endpos
 
     # Ignore leading and trailing whitespace
-    while Unicode.isspace(sbuff[startpos]) && startpos <= endpos
+    while isspace(sbuff[startpos]) && startpos <= endpos
         startpos = nextind(sbuff, startpos)
     end
-    while Unicode.isspace(sbuff[endpos]) && endpos >= startpos
+    while isspace(sbuff[endpos]) && endpos >= startpos
         endpos = prevind(sbuff, endpos)
     end
 
@@ -185,7 +185,7 @@ function tryparse_internal(::Type{Bool}, sbuff::Union{String,SubString{String}},
 
     if raise
         substr = SubString(sbuff, orig_start, orig_end) # show input string in the error to avoid confusion
-        if all(Unicode.isspace, substr)
+        if all(isspace, substr)
             throw(ArgumentError("input string only contains whitespace"))
         else
             throw(ArgumentError("invalid Bool representation: $(repr(substr))"))
@@ -272,7 +272,7 @@ tryparse_internal(::Type{Float16}, s::AbstractString, startpos::Int, endpos::Int
 
 function tryparse_internal(::Type{Complex{T}}, s::Union{String,SubString{String}}, i::Int, e::Int, raise::Bool) where {T<:Real}
     # skip initial whitespace
-    while i ≤ e && Unicode.isspace(s[i])
+    while i ≤ e && isspace(s[i])
         i = nextind(s, i)
     end
     if i > e

diff --git a/base/pkg/entry.jl b/base/pkg/entry.jl
@@ -92,7 +92,7 @@ function available()
     for (pkg, vers) in all_avail
         any(x->Types.satisfies("julia", VERSION, x[2].requires), vers) && push!(avail, pkg)
     end
-    sort!(avail, by=Base.Unicode.lowercase)
+    sort!(avail, by=lowercase)
 end
 
 function available(pkg::AbstractString)

diff --git a/base/pkg/reqs.jl b/base/pkg/reqs.jl
@@ -78,7 +78,7 @@ function write(io::IO, lines::Vector{Line})
     end
 end
 function write(io::IO, reqs::Requires)
-    for pkg in sort!(collect(keys(reqs)), by=Unicode.lowercase)
+    for pkg in sort!(collect(keys(reqs)), by=lowercase)
         println(io, Requirement(pkg, reqs[pkg]).content)
     end
 end

diff --git a/base/precompile.jl b/base/precompile.jl
@@ -60,7 +60,6 @@ precompile(Tuple{typeof(Base.lstrip), Base.SubString{String}, Array{Char, 1}})
 precompile(Tuple{getfield(Base, Symbol("#kw##split")), Array{Any, 1}, typeof(Base.split), String, Char})
 precompile(Tuple{getfield(Base, Symbol("#kw##split")), Array{Any, 1}, typeof(Base.split), Base.SubString{String}, Char})
 precompile(Tuple{typeof(Base.map!), typeof(Base.strip), Array{Base.SubString{String}, 1}, Array{Base.SubString{String}, 1}})
-precompile(Tuple{typeof(Base.Unicode.isnumeric), Base.SubString{String}})
 precompile(Tuple{Type{Core.Inference.Generator{I, F} where F where I}, Type{Core.Inference.Const}, Tuple{Tuple{Base.DevNullStream, Base.DevNullStream, Base.DevNullStream}}})
 precompile(Tuple{Type{Core.Inference.Generator{Tuple{Tuple{Base.DevNullStream, Base.DevNullStream, Base.DevNullStream}}, Type{Core.Inference.Const}}}, Type{Core.Inference.Const}, Tuple{Tuple{Base.DevNullStream, Base.DevNullStream, Base.DevNullStream}}})
 precompile(Tuple{typeof(Core.Inference.convert), Type{Tuple{Tuple{Base.DevNullStream, Base.DevNullStream, Base.DevNullStream}}}, Tuple{Tuple{Base.DevNullStream, Base.DevNullStream, Base.DevNullStream}}})
@@ -745,7 +744,6 @@ precompile(Tuple{Type{Base.Generator{I, F} where F where I}, typeof(Base.string)
 precompile(Tuple{typeof(Base._collect), Array{Any, 1}, Base.Generator{Array{Any, 1}, typeof(Base.string)}, Base.EltypeUnknown, Base.HasShape})
 precompile(Tuple{typeof(Base.similar), Array{Any, 1}, Type{String}, Tuple{Base.OneTo{Int64}}})
 precompile(Tuple{typeof(Base.collect_to!), Array{String, 1}, Base.Generator{Array{Any, 1}, typeof(Base.string)}, Int64, Int64})
-precompile(Tuple{typeof(Base.Unicode.isalpha), Char})
 precompile(Tuple{getfield(Base.Docs, Symbol("#kw##matchinds")), Array{Any, 1}, typeof(Base.Docs.matchinds), String, String})
 precompile(Tuple{typeof(Base.Docs.bestmatch), String, String})
 precompile(Tuple{typeof(Base.length), Tuple{DataType, DataType}})
@@ -908,7 +906,6 @@ precompile(Tuple{typeof(Base.lstrip), String, Char})
 precompile(Tuple{typeof(Base.Markdown.blockquote), Base.GenericIOBuffer{Array{UInt8, 1}}, Base.Markdown.MD})
 precompile(Tuple{getfield(Base.Markdown, Symbol("#kw##parse")), Array{Any, 1}, typeof(Base.Markdown.parse), String})
 precompile(Tuple{typeof(Base.Markdown.admonition), Base.GenericIOBuffer{Array{UInt8, 1}}, Base.Markdown.MD})
-precompile(Tuple{typeof(Base.Unicode.isupper), Char})
 precompile(Tuple{getfield(Base.Markdown, Symbol("#kw##linecontains")), Array{Any, 1}, typeof(Base.Markdown.linecontains), Base.GenericIOBuffer{Array{UInt8, 1}}, String})
 precompile(Tuple{typeof(Base.ucfirst), Base.SubString{String}})
 precompile(Tuple{typeof(Base.Markdown.blocktex), Base.GenericIOBuffer{Array{UInt8, 1}}, Base.Markdown.MD})

diff --git a/base/printf.jl b/base/printf.jl
@@ -3,7 +3,6 @@
 module Printf
 using Base.Grisu
 using Base.GMP
-using Base.Unicode: lowercase, textwidth, isupper
 
 ### printf formatter generation ###
 const SmallFloatingPoint = Union{Float64,Float32,Float16}

diff --git a/base/process.jl b/base/process.jl
@@ -138,7 +138,7 @@ struct FileRedirect
     filename::AbstractString
     append::Bool
     function FileRedirect(filename, append)
-        if Unicode.lowercase(filename) == (@static Sys.iswindows() ? "nul" : "/dev/null")
+        if lowercase(filename) == (@static Sys.iswindows() ? "nul" : "/dev/null")
             @warn "For portability use DevNull instead of a file redirect" maxlog=1
         end
         new(filename, append)

diff --git a/base/random/misc.jl b/base/random/misc.jl
@@ -430,7 +430,7 @@ UInt128(u::UUID) = u.value
 let groupings = [1:8; 10:13; 15:18; 20:23; 25:36]
     global UUID
     function UUID(s::AbstractString)
-        s = Base.Unicode.lowercase(s)
+        s = lowercase(s)
 
         if !contains(s, r"^[0-9a-f]{8}(?:-[0-9a-f]{4}){3}-[0-9a-f]{12}$")
             throw(ArgumentError("Malformed UUID string"))

diff --git a/base/regex.jl b/base/regex.jl
@@ -323,11 +323,11 @@ function _replace(io, repl_s::SubstitutionString, str, r, re)
             if repl[next_i] == SUB_CHAR
                 write(io, SUB_CHAR)
                 i = nextind(repl, next_i)
-            elseif Unicode.isdigit(repl[next_i])
+            elseif isdigit(repl[next_i])
                 group = parse(Int, repl[next_i])
                 i = nextind(repl, next_i)
                 while i <= e
-                    if Unicode.isdigit(repl[i])
+                    if isdigit(repl[i])
                         group = 10group + parse(Int, repl[i])
                         i = nextind(repl, i)
                     else
@@ -349,7 +349,7 @@ function _replace(io, repl_s::SubstitutionString, str, r, re)
                 end
                 #  TODO: avoid this allocation
                 groupname = SubString(repl, groupstart, prevind(repl, i))
-                if all(Unicode.isdigit, groupname)
+                if all(isdigit, groupname)
                     _write_capture(io, re, parse(Int, groupname))
                 else
                     group = PCRE.substring_number_from_name(re.regex, groupname)

diff --git a/base/repl/LineEdit.jl b/base/repl/LineEdit.jl
@@ -9,8 +9,6 @@ import ..Terminals: raw!, width, height, cmove, getX,
 
 import Base: ensureroom, peek, show, AnyDict, position
 
-using Base.Unicode: lowercase, uppercase, ucfirst, textwidth, isspace
-
 abstract type TextInterface end
 abstract type ModeState end
 

diff --git a/base/repl/REPL.jl b/base/repl/REPL.jl
@@ -1090,7 +1090,7 @@ function ends_with_semicolon(line::AbstractString)
             else
                 # outside of a comment, encountering anything but whitespace
                 # means the semi-colon was internal to the expression
-                Base.Unicode.isspace(c) || return false
+                isspace(c) || return false
             end
         end
         return true