Skip to content

Commit 73fed22

Browse files
ScottPJonesScottPJones
committed
Adapt for ChrBase fixes
1 parent 11ba0a6 commit 73fed22

File tree

8 files changed

+130
-486
lines changed

8 files changed

+130
-486
lines changed

‎REQUIRE

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,4 +3,4 @@ MurmurHash3 0.1.5
33
ModuleInterfaceTools 0.1.7
44
StrAPI 0.1.8
55
CharSetEncodings 0.1.8
6-
ChrBase 0.1.8
6+
ChrBase 0.1.9

‎src/StrBase.jl

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,6 @@ include("types.jl")
4848
@static V6_COMPAT && include("compat.jl")
4949
@static NEW_ITERATE && include("fixparse.jl")
5050
include("chars.jl")
51-
include("charcase.jl")
5251
include("access.jl")
5352
include("traits.jl")
5453
include("utf8proc.jl")

‎src/casefold.jl

Lines changed: 29 additions & 26 deletions
Original file line numberDiff line numberDiff line change
@@ -5,12 +5,15 @@ Copyright 2017-2018 Gandalf Software, Inc., Scott P. Jones
55
Licensed under MIT License, see LICENSE.md
66
=#
77

8+
const _wide_upper = ChrBase._wide_upper
9+
const _wide_lower_latin = ChrBase._wide_lower_latin
10+
811
function uppercase_first(str::MaybeSub{S}) where {C<:ASCIICSE,S<:Str{C}}
912
(len = ncodeunits(str)) == 0 && return str
1013
@preserve str begin
1114
pnt = pointer(str)
1215
ch = get_codeunit(pnt)
13-
_islower_a(ch) || return str
16+
_is_lower_a(ch) || return str
1417
buf, out = _allocate(UInt8, len)
1518
unsafe_copyto!(out, pnt, len)
1619
set_codeunit!(out, ch - 0x20)
@@ -23,7 +26,7 @@ function lowercase_first(str::MaybeSub{S}) where {C<:ASCIICSE,S<:Str{C}}
2326
@preserve str begin
2427
pnt = pointer(str)
2528
ch = get_codeunit(pnt)
26-
_isupper_a(ch) || return str
29+
_is_upper_a(ch) || return str
2730
buf, out = _allocate(UInt8, len)
2831
unsafe_copyto!(out, pnt, len)
2932
set_codeunit!(out, ch + 0x20)
@@ -38,7 +41,7 @@ function _upper(::Type{C}, beg::Ptr{UInt8}, off, len) where {C<:ASCIICSE}
3841
out += off
3942
while out < fin
4043
ch = get_codeunit(out)
41-
_islower_a(ch) && set_codeunit!(out, ch - 0x20)
44+
_is_lower_a(ch) && set_codeunit!(out, ch - 0x20)
4245
out += 1
4346
end
4447
Str(C, buf)
@@ -51,7 +54,7 @@ function _lower(::Type{C}, beg::Ptr{UInt8}, off, len) where {C<:ASCIICSE}
5154
out += off
5255
while out < fin
5356
ch = get_codeunit(out)
54-
_isupper_a(ch) && set_codeunit!(out, ch + 0x20)
57+
_is_upper_a(ch) && set_codeunit!(out, ch + 0x20)
5558
out += 1
5659
end
5760
Str(C, buf)
@@ -64,7 +67,7 @@ function _upper(::Type{C}, beg::Ptr{UInt8}, off, len) where {C<:LatinCSE}
6467
out += off
6568
while out < fin
6669
ch = get_codeunit(out)
67-
_can_upper(ch) && set_codeunit!(out, ch - 0x20)
70+
_can_upper_al(ch) && set_codeunit!(out, ch - 0x20)
6871
out += 1
6972
end
7073
Str(C, buf)
@@ -76,7 +79,7 @@ function uppercase(str::MaybeSub{S}) where {C<:ASCIICSE,S<:Str{C}}
7679
pnt = beg = pointer(str)
7780
fin = beg + len
7881
while pnt < fin
79-
_islower_a(get_codeunit(pnt)) && return _upper(C, beg, pnt-beg, len)
82+
_is_lower_a(get_codeunit(pnt)) && return _upper(C, beg, pnt-beg, len)
8083
pnt += 1
8184
end
8285
end
@@ -89,7 +92,7 @@ function lowercase(str::MaybeSub{S}) where {C<:ASCIICSE,S<:Str{C}}
8992
pnt = beg = pointer(str)
9093
fin = beg + len
9194
while pnt < fin
92-
_isupper_a(get_codeunit(pnt)) && return _lower(C, beg, pnt-beg, len)
95+
_is_upper_a(get_codeunit(pnt)) && return _lower(C, beg, pnt-beg, len)
9396
pnt += 1
9497
end
9598
end
@@ -101,7 +104,7 @@ function uppercase_first(str::MaybeSub{S}) where {C<:LatinCSE,S<:Str{C}}
101104
@preserve str begin
102105
pnt = pointer(str)
103106
ch = get_codeunit(pnt)
104-
_can_upper(ch) || return str
107+
_can_upper_al(ch) || return str
105108
buf, out = _allocate(UInt8, len)
106109
set_codeunit!(out, ch - 0x20)
107110
len > 1 && unsafe_copyto!(out + 1, pnt+1, len-1)
@@ -118,9 +121,9 @@ function uppercase_first(str::MaybeSub{S}) where {C<:_LatinCSE,S<:Str{C}}
118121
if _wide_lower_latin(ch)
119122
buf, out = _allocate(UInt16, len)
120123
_widen!(out, pnt, pnt + len)
121-
set_codeunit!(out, _wide_out_upper(ch))
124+
set_codeunit!(out, _wide_upper(ch))
122125
Str(_UCS2CSE, buf)
123-
elseif _can_upper(ch)
126+
elseif _can_upper_al(ch)
124127
buf8, out8 = _allocate(UInt8, len)
125128
len > 1 && unsafe_copyto!(out8, pnt, len)
126129
set_codeunit!(out8, ch - 0x20)
@@ -136,7 +139,7 @@ function lowercase_first(str::MaybeSub{S}) where {C<:Latin_CSEs,S<:Str{C}}
136139
@preserve str begin
137140
pnt = pointer(str)
138141
ch = get_codeunit(pnt)
139-
_isupper_al(ch) || return str
142+
_is_upper_al(ch) || return str
140143
buf, out = _allocate(UInt8, len)
141144
set_codeunit!(out, ch + 0x20)
142145
len > 1 && unsafe_copyto!(out+1, pnt+1, len-1)
@@ -158,7 +161,7 @@ function _upper(::Type{C}, beg::Ptr{UInt8}, off, len) where {C<:_LatinCSE}
158161
out += off
159162
while out < fin
160163
ch = get_codeunit(out)
161-
_can_upper(ch) && set_codeunit!(out, ch - 0x20)
164+
_can_upper_al(ch) && set_codeunit!(out, ch - 0x20)
162165
out += 1
163166
end
164167
Str(C, buf)
@@ -182,7 +185,7 @@ function _widenupper(beg::Ptr{UInt8}, off, len)
182185
out = bytoff(out, off)
183186
while out < fin
184187
ch = get_codeunit(cur)
185-
set_codeunit!(out, _can_upper(ch) ? ch - 0x20 : _wide_out_upper(ch))
188+
set_codeunit!(out, _can_upper_al(ch) ? (ch - 0x20) : _wide_upper(ch))
186189
cur += 1
187190
out += 2
188191
end
@@ -195,7 +198,7 @@ function uppercase(str::MaybeSub{S}) where {C<:LatinCSE,S<:Str{C}}
195198
pnt = beg = pointer(str)
196199
fin = beg + len
197200
while pnt < fin
198-
_can_upper(get_codeunit(pnt)) && return _upper(C, beg, pnt-beg, len)
201+
_can_upper_al(get_codeunit(pnt)) && return _upper(C, beg, pnt-beg, len)
199202
pnt += 1
200203
end
201204
end
@@ -210,7 +213,7 @@ function uppercase(str::MaybeSub{S}) where {C<:_LatinCSE,S<:Str{C}}
210213
while pnt < fin
211214
ch = get_codeunit(pnt)
212215
_wide_lower_latin(ch) && return _widenupper(beg, pnt-beg, len)
213-
_can_upper(ch) && return _upper(C, beg, pnt-beg, len)
216+
_can_upper_al(ch) && return _upper(C, beg, pnt-beg, len)
214217
pnt += 1
215218
end
216219
end
@@ -224,7 +227,7 @@ function _lower(::Type{C}, beg::Ptr{UInt8}, off, len) where {C<:Latin_CSEs}
224227
out += off
225228
while out < fin
226229
ch = get_codeunit(out)
227-
_isupper_al(ch) && set_codeunit!(out, ch + 0x20)
230+
_is_upper_al(ch) && set_codeunit!(out, ch + 0x20)
228231
out += 1
229232
end
230233
Str(C, buf)
@@ -236,7 +239,7 @@ function lowercase(str::MaybeSub{S}) where {C<:Latin_CSEs,S<:Str{C}}
236239
pnt = beg = pointer(str)
237240
fin = beg + len
238241
while pnt < fin
239-
_isupper_al(get_codeunit(pnt)) && return _lower(C, beg, pnt-beg, len)
242+
_is_upper_al(get_codeunit(pnt)) && return _lower(C, beg, pnt-beg, len)
240243
pnt += 1
241244
end
242245
end
@@ -259,9 +262,9 @@ function _lower(::Type{C}, beg, off, len) where {C<:_UCS2CSE}
259262
while out < fin
260263
ch = get_codeunit(out)
261264
if ch <= 0x7f
262-
_isupper_a(ch) && set_codeunit!(out, ch += 0x20)
265+
_is_upper_a(ch) && set_codeunit!(out, ch += 0x20)
263266
elseif ch <= 0xff
264-
_isupper_l(ch) && set_codeunit!(out, ch += 0x20)
267+
_is_upper_l(ch) && set_codeunit!(out, ch += 0x20)
265268
elseif ch <= 0xffff
266269
if _can_lower_bmp(ch)
267270
ch = _lower_bmp(ch)
@@ -289,7 +292,7 @@ function _lower(::Type{C}, beg, off, len) where {C<:Union{UCS2CSE,UTF32_CSEs}}
289292
while out < fin
290293
ch = get_codeunit(out)
291294
if ch <= 0xff
292-
_isupper_al(ch) && set_codeunit!(out, ch += 0x20)
295+
_is_upper_al(ch) && set_codeunit!(out, ch += 0x20)
293296
elseif ch <= 0xffff
294297
_can_lower_bmp(ch) && set_codeunit!(out, _lower_bmp(ch))
295298
elseif ch <= 0x1ffff
@@ -305,10 +308,10 @@ function lowercase_first(str::MaybeSub{S}) where {C<:_UCS2CSE,S<:Str{C}}
305308
@preserve str begin
306309
pnt = pointer(str)
307310
ch = get_codeunit(pnt)
308-
(ch <= 0xff ? _isupper_al(ch) : ch <= 0xffff ? _can_lower_bmp(ch) :
309-
ch <= 0x1ffff && _can_lower_slp(ch)) ||
311+
(ch <= 0xff ? _is_upper_al(ch) : ch <= 0xffff ? _can_lower_bmp(ch) :
312+
(ch <= 0x1ffff && _can_lower_slp(ch))) ||
310313
return str
311-
cl = _lower_ch(ch)
314+
cl = _lowercase(ch)
312315
if ch > 0xff && cl <= 0xff && _check_mask_ul(pnt+1, len-1, _latin_mask(UInt16))
313316
buf8, out8 = _allocate(UInt8, len)
314317
len > 1 && _narrow!(out8, pnt, pnt + len)
@@ -328,7 +331,7 @@ function uppercase_first(str::MaybeSub{S}) where {C<:Union{UCS2_CSEs,UTF32_CSEs}
328331
@preserve str begin
329332
pnt = pointer(str)
330333
ch = get_codeunit(pnt)
331-
cp = _title_ch(ch)
334+
cp = _titlecase(ch)
332335
ch == cp && return str
333336
buf, out = _allocate(codeunit(C), len)
334337
len > 1 && unsafe_copyto!(out, pnt, len)
@@ -345,7 +348,7 @@ function lowercase_first(str::MaybeSub{S}) where {C<:Union{UCS2CSE,UTF32_CSEs},S
345348
_can_lower_ch(ch) || return str
346349
buf, out = _allocate(codeunit(C), len)
347350
len > 1 && unsafe_copyto!(out, pnt, len)
348-
set_codeunit!(out, _lower_ch(ch))
351+
set_codeunit!(out, _lowercase(ch))
349352
Str(C, buf)
350353
end
351354
end
@@ -372,7 +375,7 @@ function _upper(::Type{C}, beg, off, len) where {C<:Union{UCS2_CSEs,UTF32_CSEs}}
372375
while out < fin
373376
ch = get_codeunit(out)
374377
if ch <= 0x7f
375-
_islower_a(ch) && set_codeunit!(out, ch -= 0x20)
378+
_is_lower_a(ch) && set_codeunit!(out, ch -= 0x20)
376379
elseif ch <= 0xff
377380
set_codeunit!(out, _uppercase_l(ch))
378381
elseif ch <= 0xffff

‎src/charcase.jl

Lines changed: 0 additions & 103 deletions
This file was deleted.

0 commit comments

Comments
 (0)