Browse Source

utf8 fixes

pull/4/head
asie 7 years ago
parent
commit
494c22c408
  1. 2
      Makefile
  2. 2
      include/luares.h
  3. 22
      src/c/lnative.c
  4. 4
      src/c/modules.c
  5. 4
      src/lua/core/init.lua
  6. 82
      src/lua/core/sandbox.lua
  7. 4
      src/lua/core/textgpu.lua
  8. 328
      src/lua/core/utf8/utf8.lua
  9. 1861
      src/lua/core/utf8/utf8data.lua

2
Makefile

@ -59,4 +59,4 @@ smallclean:
# Other
.PHONY: clean cleanresourcues resources build smallclean all
.PHONY: clean cleanresourcues resources build smallclean all

2
include/luares.h

@ -8,8 +8,6 @@ extern char lua_filesystem[];
extern char lua_init[];
extern char lua_sandbox[];
extern char lua_textgpu[];
extern char lua_utf8_utf8data[];
extern char lua_utf8_utf8[];
extern char lua_util_color[];
extern char lua_util_random[];
#endif

22
src/c/lnative.c

@ -15,6 +15,7 @@
#include <fcntl.h>
#include <dirent.h>
#include <ftw.h>
#include <wchar.h>
#include <limits.h>
#include <linux/kd.h>
@ -350,6 +351,21 @@ static int l_pull (lua_State *L) {
return 1;
}
static int l_wcwidth (lua_State *L) {
lua_pushnumber(L, wcwidth(lua_tonumber(L, 1)));
return 1;
}
static int l_towupper (lua_State *L) {
lua_pushnumber(L, towupper(lua_tonumber(L, 1)));
return 1;
}
static int l_towlower (lua_State *L) {
lua_pushnumber(L, towlower(lua_tonumber(L, 1)));
return 1;
}
void luanative_start(lua_State *L) {
lua_createtable (L, 0, 1);
@ -371,6 +387,10 @@ void luanative_start(lua_State *L) {
pushctuple(L, "fs_size", l_fs_size);
pushctuple(L, "fs_read", l_fs_read);
pushctuple(L, "wcwidth", l_wcwidth);
pushctuple(L, "towlower", l_towlower);
pushctuple(L, "towupper", l_towupper);
pushctuple(L, "beep", l_beep);
pushctuple(L, "uptime", l_uptime);
pushctuple(L, "totalMemory", l_totalMemory);
@ -378,4 +398,4 @@ void luanative_start(lua_State *L) {
pushctuple(L, "pull", l_pull);
lua_setglobal(L, "native");
}
}

4
src/c/modules.c

@ -18,10 +18,8 @@ void setup_modules(lua_State *L) {
pushstuple(L, "textgpu", lua_textgpu);
pushstuple(L, "color", lua_util_color);
pushstuple(L, "random", lua_util_random);
pushstuple(L, "utf8data", lua_utf8_utf8data);
pushstuple(L, "utf8", lua_utf8_utf8);
pushstuple(L, "eepromDefault", res_eepromDefault);
lua_setglobal(L, "moduleCode");
}
}

4
src/lua/core/init.lua

@ -43,8 +43,6 @@ function main()
--Utils
loadModule("random")
loadModule("color")
loadModule("utf8data")
loadModule("utf8")
modules.address = modules.random.uuid() --TODO: PREALPHA: Make constant
@ -88,4 +86,4 @@ for k, hook in ipairs(deadhooks) do
print("Shutdown hook with following error:")
print(cause)
end
end
end

82
src/lua/core/sandbox.lua

@ -1,4 +1,14 @@
local sandbox
local l_wlen = function(text)
checkArg(1, text, "string")
local i = 0
for p, c in utf8.codes(text) do
i = i + native.wcwidth(c)
end
return utf8.len(text)
end
sandbox = {
assert = assert,
dofile = nil,
@ -163,20 +173,72 @@ sandbox = {
unicode = {
char = utf8.char,
charWidth = function(c)
checkArg(1, c, "string")
return modules.utf8.charbytes(c)
return l_wlen(c)
end,
isWide = function(c)
checkArg(1, c, "string")
return modules.utf8.charbytes(c) > 1
return l_wlen(c) > 1
end,
len = utf8.len,
lower = modules.utf8.lower,
reverse = modules.utf8.reverse,
sub = modules.utf8.sub,
upper = modules.utf8.upper,
wlen = utf8.len, --How is it different from len?
--wtrunc?
lower = function(text)
checkArg(1, text, "string")
local s = ""
for p, c in utf8.codes(text) do
s = s .. utf8.char(native.towlower(c))
end
return s
end,
upper = function(text)
checkArg(1, text, "string")
local s = ""
for p, c in utf8.codes(text) do
s = s .. utf8.char(native.towupper(c))
end
return s
end,
reverse = function(text)
checkArg(1, text, "string")
local s = ""
for p, c in utf8.codes(text) do
s = utf8.char(c) .. s
end
return s
end,
sub = function(s, i, j)
checkArg(1, s, "string")
i = i or 1
j = j or math.maxinteger
if i<1 or j<1 then
local n = utf8.len(s)
if not n then return nil end
if i<0 then i = n+1+i end
if j<0 then j = n+1+j end
if i<0 then i = 1 elseif i>n then i = n end
if j<0 then j = 1 elseif j>n then j = n end
end
if j<i then return "" end
i = utf8.offset(s,i) or math.maxinteger
j = utf8.offset(s,j+1) or math.maxinteger
if i and j then return s:sub(i,j-1)
elseif i then return s:sub(i)
else return ""
end
end,
wlen = l_wlen,
wtrunc = function(s, l)
checkArg(1, s, "string")
checkArg(2, l, "number")
local width = 0
local text = ""
for p, c in utf8.codes(s) do
if width < l then
width = width + native.wcwidth(c)
if width < l then
text = text .. utf8.char(c)
end
end
end
return text
end,
},
checkArg = checkArg,
og = _G

4
src/lua/core/textgpu.lua

@ -39,7 +39,7 @@ local function prepareBuffers(w, h)
end
end
local usub = modules.utf8.sub
local usub = modules.sandbox.utf8.sub
local function insertString(main, sub, at)
return usub(main, 1, at - 1) .. sub .. usub(main, at + utf8.len(sub))
end
@ -234,4 +234,4 @@ function textgpu.start()
end
end
return textgpu
return textgpu

328
src/lua/core/utf8/utf8.lua

@ -1,328 +0,0 @@
-- $Id: utf8.lua 179 2009-04-03 18:10:03Z pasta $
--
-- Provides UTF-8 aware string functions implemented in pure lua:
-- * string.utf8len(s)
-- * string.utf8sub(s, i, j)
-- * string.utf8reverse(s)
--
-- If utf8data.lua (containing the lower<->upper case mappings) is loaded, these
-- additional functions are available:
-- * string.utf8upper(s)
-- * string.utf8lower(s)
--
-- All functions behave as their non UTF-8 aware counterparts with the exception
-- that UTF-8 characters are used instead of bytes for all units.
--[[
Copyright (c) 2006-2007, Kyle Smith
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the author nor the names of its contributors may be
used to endorse or promote products derived from this software without
specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
--]]
-- ABNF from RFC 3629
--
-- UTF8-octets = *( UTF8-char )
-- UTF8-char = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
-- UTF8-1 = %x00-7F
-- UTF8-2 = %xC2-DF UTF8-tail
-- UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
-- %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
-- UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
-- %xF4 %x80-8F 2( UTF8-tail )
-- UTF8-tail = %x80-BF
--
local strbyte, strlen, strsub, type = string.byte, string.len, string.sub, type
local lutf8 = utf8
local utf8 = {}
-- returns the number of bytes used by the UTF-8 character at byte i in s
-- also doubles as a UTF-8 character validator
local function utf8charbytes(s, i)
-- argument defaults
i = i or 1
-- argument checking
if type(s) ~= "string" then
error("bad argument #1 to 'utf8charbytes' (string expected, got ".. type(s).. ")")
end
if type(i) ~= "number" then
error("bad argument #2 to 'utf8charbytes' (number expected, got ".. type(i).. ")")
end
local c = strbyte(s, i)
-- determine bytes needed for character, based on RFC 3629
-- validate byte 1
if c > 0 and c <= 127 then
-- UTF8-1
return 1
elseif c >= 194 and c <= 223 then
-- UTF8-2
local c2 = strbyte(s, i + 1)
if not c2 then
error("UTF-8 string terminated early")
end
-- validate byte 2
if c2 < 128 or c2 > 191 then
error("Invalid UTF-8 character")
end
return 2
elseif c >= 224 and c <= 239 then
-- UTF8-3
local c2 = strbyte(s, i + 1)
local c3 = strbyte(s, i + 2)
if not c2 or not c3 then
error("UTF-8 string terminated early")
end
-- validate byte 2
if c == 224 and (c2 < 160 or c2 > 191) then
error("Invalid UTF-8 character")
elseif c == 237 and (c2 < 128 or c2 > 159) then
error("Invalid UTF-8 character")
elseif c2 < 128 or c2 > 191 then
error("Invalid UTF-8 character")
end
-- validate byte 3
if c3 < 128 or c3 > 191 then
error("Invalid UTF-8 character")
end
return 3
elseif c >= 240 and c <= 244 then
-- UTF8-4
local c2 = strbyte(s, i + 1)
local c3 = strbyte(s, i + 2)
local c4 = strbyte(s, i + 3)
if not c2 or not c3 or not c4 then
error("UTF-8 string terminated early")
end
-- validate byte 2
if c == 240 and (c2 < 144 or c2 > 191) then
error("Invalid UTF-8 character")
elseif c == 244 and (c2 < 128 or c2 > 143) then
error("Invalid UTF-8 character")
elseif c2 < 128 or c2 > 191 then
error("Invalid UTF-8 character")
end
-- validate byte 3
if c3 < 128 or c3 > 191 then
error("Invalid UTF-8 character")
end
-- validate byte 4
if c4 < 128 or c4 > 191 then
error("Invalid UTF-8 character")
end
return 4
else
error("Invalid UTF-8 character")
end
end
utf8.charbytes = utf8charbytes
-- returns the number of characters in a UTF-8 string
local function utf8len(s)
-- argument checking
if type(s) ~= "string" then
error("bad argument #1 to 'utf8len' (string expected, got ".. type(s).. ")")
end
local pos = 1
local bytes = strlen(s)
local len = 0
while pos <= bytes do
len = len + 1
pos = pos + utf8charbytes(s, pos)
end
return len
end
utf8.len = utf8len
-- functions identically to string.sub except that i and j are UTF-8 characters
-- instead of bytes
local function utf8sub(s, i, j)
-- argument defaults
j = j or -1
-- argument checking
if type(s) ~= "string" then
error("bad argument #1 to 'utf8sub' (string expected, got ".. type(s).. ")")
end
if type(i) ~= "number" then
error("bad argument #2 to 'utf8sub' (number expected, got ".. type(i).. ")")
end
if type(j) ~= "number" then
error("bad argument #3 to 'utf8sub' (number expected, got ".. type(j).. ")")
end
local pos = 1
local bytes = strlen(s)
local len = 0
-- only set l if i or j is negative
local l = (i >= 0 and j >= 0) or utf8len(s)
local startChar = (i >= 0) and i or l + i + 1
local endChar = (j >= 0) and j or l + j + 1
-- can't have start before end!
if startChar > endChar then
return ""
end
-- byte offsets to pass to string.sub
local startByte, endByte = 1, bytes
while pos <= bytes do
len = len + 1
if len == startChar then
startByte = pos
end
pos = pos + utf8charbytes(s, pos)
if len == endChar then
endByte = pos - 1
break
end
end
return strsub(s, startByte, endByte)
end
function utf8.sub(s,i,j)
i = i or 1
j = j or math.maxinteger
if i<1 or j<1 then
local n = lutf8.len(s)
if not n then return nil end
if i<0 then i = n+1+i end
if j<0 then j = n+1+j end
if i<0 then i = 1 elseif i>n then i = n end
if j<0 then j = 1 elseif j>n then j = n end
end
if j<i then return "" end
i = lutf8.offset(s,i) or math.maxinteger
j = lutf8.offset(s,j+1) or math.maxinteger
if i and j then return s:sub(i,j-1)
elseif i then return s:sub(i)
else return ""
end
end
--utf8.sub = utf8sub
-- replace UTF-8 characters based on a mapping table
local function utf8replace(s, mapping)
-- argument checking
if type(s) ~= "string" then
error("bad argument #1 to 'utf8replace' (string expected, got ".. type(s).. ")")
end
if type(mapping) ~= "table" then
error("bad argument #2 to 'utf8replace' (table expected, got ".. type(mapping).. ")")
end
local pos = 1
local bytes = strlen(s)
local charbytes
local newstr = ""
while pos <= bytes do
charbytes = utf8charbytes(s, pos)
local c = strsub(s, pos, pos + charbytes - 1)
newstr = newstr .. (mapping[c] or c)
pos = pos + charbytes
end
return newstr
end
-- identical to string.upper except it knows about unicode simple case conversions
local function utf8upper(s)
return utf8replace(s, modules.utf8data.lc_uc)
end
utf8.upper = utf8upper
-- identical to string.lower except it knows about unicode simple case conversions
local function utf8lower(s)
return utf8replace(s, modules.utf8data.uc_lc)
end
utf8.lower = utf8lower
-- identical to string.reverse except that it supports UTF-8
local function utf8reverse(s)
-- argument checking
if type(s) ~= "string" then
error("bad argument #1 to 'utf8reverse' (string expected, got ".. type(s).. ")")
end
local bytes = strlen(s)
local pos = bytes
local charbytes
local newstr = ""
while pos > 0 do
c = strbyte(s, pos)
while c >= 128 and c <= 191 do
pos = pos - 1
c = strbyte(pos)
end
charbytes = utf8charbytes(s, pos)
newstr = newstr .. strsub(s, pos, pos + charbytes - 1)
pos = pos - 1
end
return newstr
end
utf8.reverse = utf8reverse
return utf8

1861
src/lua/core/utf8/utf8data.lua

File diff suppressed because it is too large
Loading…
Cancel
Save