more verbose multi-line display(c) for Char (#19847)

* more verbose multi-line display(c) for Char

base/char.jl

@@ -77,3 +77,10 @@ function show(io::IO, c::Char)
  end
  return
 end
+
+function show(io::IO, ::MIME"text/plain", c::Char)
+ show(io, c)
+ u = UInt32(c)
+ print(io, ": ", isascii(c) ? "ASCII/" : "", "Unicode U+", hex(u, u > 0xffff ? 6 : 4))
+ print(io, " (category ", UTF8proc.category_abbrev(c), ": ", UTF8proc.category_string(c), ")")
+end

base/multimedia.jl

@@ -11,17 +11,16 @@ export Display, display, pushdisplay, popdisplay, displayable, redisplay,
 # that Julia's dispatch and overloading mechanisms can be used to
 # dispatch show and to add conversions for new types.
 
-immutable MIME{mime} end
+# defined in sysimg.jl for bootstrapping:
+# immutable MIME{mime} end
+# macro MIME_str(s)
+import Base: MIME, @MIME_str
 
 import Base: show, print, string, convert
 MIME(s) = MIME{Symbol(s)}()
 show{mime}(io::IO, ::MIME{mime}) = print(io, "MIME type ", string(mime))
 print{mime}(io::IO, ::MIME{mime}) = print(io, mime)
 
-macro MIME_str(s)
- :(MIME{$(Expr(:quote, Symbol(s)))})
-end
-
 ###########################################################################
 # For any type T one can define show(io, ::MIME"type", x::T) = ...
 # in order to provide a way to export T as a given mime type.

base/strings/utf8proc.jl

@@ -5,7 +5,7 @@ module UTF8proc
 
 import Base: show, ==, hash, string, Symbol, isless, length, eltype, start, next, done, convert, isvalid, lowercase, uppercase, titlecase
 
-export isgraphemebreak
+export isgraphemebreak, category_code, category_abbrev, category_string
 
 # also exported by Base:
 export normalize_string, graphemes, is_assigned_char, charwidth, isvalid,
@@ -51,6 +51,40 @@ const UTF8PROC_CATEGORY_CF = 27
 const UTF8PROC_CATEGORY_CS = 28
 const UTF8PROC_CATEGORY_CO = 29
 
+# strings corresponding to the category constants
+const category_strings = [
+ "Other, not assigned",
+ "Letter, uppercase",
+ "Letter, lowercase",
+ "Letter, titlecase",
+ "Letter, modifier",
+ "Letter, other",
+ "Mark, nonspacing",
+ "Mark, spacing combining",
+ "Mark, enclosing",
+ "Number, decimal digit",
+ "Number, letter",
+ "Number, other",
+ "Punctuation, connector",
+ "Punctuation, dash",
+ "Punctuation, open",
+ "Punctuation, close",
+ "Punctuation, initial quote",
+ "Punctuation, final quote",
+ "Punctuation, other",
+ "Symbol, math",
+ "Symbol, currency",
+ "Symbol, modifier",
+ "Symbol, other",
+ "Separator, space",
+ "Separator, line",
+ "Separator, paragraph",
+ "Other, control",
+ "Other, format",
+ "Other, surrogate",
+ "Other, private use"
+]
+
 const UTF8PROC_STABLE = (1<<1)
 const UTF8PROC_COMPAT = (1<<2)
 const UTF8PROC_COMPOSE = (1<<3)
@@ -164,9 +198,11 @@ titlecase(c::Char) = isascii(c) ? ('a' <= c <= 'z' ? c - 0x20 : c) : Char(ccall(
 ############################################################################
 
 # returns UTF8PROC_CATEGORY code in 0:30 giving Unicode category
-function category_code(c)
- return ccall(:utf8proc_category, Cint, (UInt32,), c)
-end
+category_code(c) = ccall(:utf8proc_category, Cint, (UInt32,), c)
+
+# more human-readable representations of the category code
+category_abbrev(c) = unsafe_string(ccall(:utf8proc_category_string, Cstring, (UInt32,), c))
+category_string(c) = category_strings[category_code(c)+1]
 
 """
  is_assigned_char(c) -> Bool

base/sysimg.jl

@@ -158,6 +158,12 @@ include("io.jl")
 include("iostream.jl")
 include("iobuffer.jl")
 
+# define MIME"foo/bar" early so that we can overload 3-arg show
+immutable MIME{mime} end
+macro MIME_str(s)
+ :(MIME{$(Expr(:quote, Symbol(s)))})
+end
+
 # strings & printing
 include("char.jl")
 include("intfuncs.jl")

test/char.jl

@@ -195,3 +195,6 @@ let
 end
 
 @test !isequal('x', 120)
+
+@test sprint(show, "text/plain", '$') == "'\$': ASCII/Unicode U+0024 (category Sc: Symbol, currency)"
+@test repr('$') == "'\$'"