Module:Unicode data/scripts/make - Revision history

Erutuon: remove separation between variable definition and use

2020-03-11T19:28:30Z

remove separation between variable definition and use

← Previous revision		Revision as of 19:28, 11 March 2020
Line 1:		Line 1:
	local p = {}		local p = {}

⚫	local ~~scripts_txt~~ = 'User:Erutuon/Unicode~~/Scripts.txt~~'
⚫	local property_value_aliases_txt = '~~User:Erutuon/Unicode~~/PropertyValueAliases.txt'

	local Array = require 'Module:Array'		local Array = require 'Module:Array'
Line 121:		Line 118:

	function p.main(frame)		function p.main(frame)
		⚫	local dir = 'User:Erutuon/Unicode'
			local scripts_txt = dir .. '/Scripts.txt'
		⚫	local property_value_aliases_txt = dir ..'/PropertyValueAliases.txt'

	return p.highlight(p.make_script_data(scripts_txt, property_value_aliases_txt))		return p.highlight(p.make_script_data(scripts_txt, property_value_aliases_txt))
	end		end

Erutuon: sort "aliases" by script code, not script name

2019-03-11T22:22:02Z

sort "aliases" by script code, not script name

← Previous revision		Revision as of 22:22, 11 March 2019
Line 97:		Line 97:

	local printed_script_name_to_code = Array()		local printed_script_name_to_code = Array()
	for name, code in require 'Module:TableTools'.sortedPairs(script_name_to_code~~) do~~		for name, code in require 'Module:TableTools'.sortedPairs(script_name_to_code,
			function(name1, name2)
			return script_name_to_code[name1] < script_name_to_code[name2]
			end) do
	printed_script_name_to_code:insert(('\t\t%s = "%s",'):format(code, name:gsub('_', ' ')))		printed_script_name_to_code:insert(('\t\t%s = "%s",'):format(code, name:gsub('_', ' ')))
	end		end

Erutuon: ranges and singles inserted in wrong positions

2019-03-11T22:20:18Z

ranges and singles inserted in wrong positions

← Previous revision		Revision as of 22:20, 11 March 2019
Line 102:		Line 102:

	local data = template		local data = template
⚫	:gsub('%.%.%.', printed_ranges:concat('\n'), 1)
	:gsub('%.%.%.', printed_singles:concat('\n'), 1)		:gsub('%.%.%.', printed_singles:concat('\n'), 1)
		⚫	:gsub('%.%.%.', printed_ranges:concat('\n'), 1)
	:gsub('%.%.%.', printed_script_name_to_code:concat('\n'), 1)		:gsub('%.%.%.', printed_script_name_to_code:concat('\n'), 1)

Erutuon: fix remaining bugs and output highlighted code

2019-03-11T22:16:48Z

fix remaining bugs and output highlighted code

← Previous revision		Revision as of 22:16, 11 March 2019
Line 1:		Line 1:
	local p = {}		local p = {}

	local scripts_txt = '~~some Wikipedia page~~'		local scripts_txt = 'User:Erutuon/Unicode/Scripts.txt'
	local property_value_aliases_txt = '~~some Wikipedia page~~'		local property_value_aliases_txt = 'User:Erutuon/Unicode/PropertyValueAliases.txt'

	local Array = require 'Module:Array'		local Array = require 'Module:Array'
Line 11:		Line 11:

	function p.make_script_name_to_code(page_name)		function p.make_script_name_to_code(page_name)
	local ~~content~~ = mw.title.new(page_name):getContent()		local property_value_aliases = assert(assert(mw.title.new(page_name)):getContent())

	local script_aliases = property_value_aliases:match(		local script_aliases = property_value_aliases:match(
Line 27:		Line 27:
	end		end

			function p.make_script_data(scripts_txt, property_value_aliases_txt)
⚫	function p.main(frame)
			local script_data = assert(assert(mw.title.new(scripts_txt)):getContent())
⚫	local script_name_to_code = p.make_script_name_to_code()

		⚫	local script_name_to_code = p.make_script_name_to_code(property_value_aliases_txt)
	setmetatable(script_name_to_code, { __index = function (self, k)		setmetatable(script_name_to_code, { __index = function (self, k)
	error(('No code for "%s"'):format(k))		error(('No code for "%s"'):format(k))
Line 53:		Line 55:

	while script_ranges[i] do		while script_ranges[i] do
	local low, high, script_code = ~~table.~~unpack(script_ranges[i])		local low, high, script_code = unpack(script_ranges[i])
	if low == high then		if low == high then
	singles[low] = script_code		singles[low] = script_code
Line 85:		Line 87:
	local printed_ranges = Array()		local printed_ranges = Array()
	for _, range in ipairs(script_ranges) do		for _, range in ipairs(script_ranges) do
	local low, high, script_code = ~~table.~~unpack(range)		local low, high, script_code = unpack(range)
	printed_ranges:insert(('\t{ 0x%05X, 0x%05X, "%s" },'):format(low, high, script_code))		printed_ranges:insert(('\t\t{ 0x%05X, 0x%05X, "%s" },'):format(low, high, script_code))
	end		end

	local printed_singles = Array()		local printed_singles = Array()
	for codepoint, script_code in require 'Module:TableTools'.sortedPairs(singles) do		for codepoint, script_code in require 'Module:TableTools'.sortedPairs(singles) do
	printed_singles:insert(('\t[0x%05X] = "%s",'):format(codepoint, script_code))		printed_singles:insert(('\t\t[0x%05X] = "%s",'):format(codepoint, script_code))
	end		end

	local printed_script_name_to_code = Array()		local printed_script_name_to_code = Array()
	for name, code in require 'Module:TableTools'.sortedPairs(script_name_to_code) do		for name, code in require 'Module:TableTools'.sortedPairs(script_name_to_code) do
	printed_script_name_to_code:insert(('%s = "%s",'):format(code, name:gsub('_', ' ')))		printed_script_name_to_code:insert(('\t\t%s = "%s",'):format(code, name:gsub('_', ' ')))
	end		end

Line 105:		Line 107:

	return data		return data
			end

			function p.highlight(lua_code)
			return mw.getCurrentFrame():extensionTag{
			name = "syntaxhighlight",
			content = lua_code,
			args = { lang = "lua" }
			}
			end

		⚫	function p.main(frame)
			return p.highlight(p.make_script_data(scripts_txt, property_value_aliases_txt))
	end		end

Erutuon: array objects

2019-03-11T22:05:26Z

array objects

← Previous revision		Revision as of 22:05, 11 March 2019
Line 1:		Line 1:
	local p = {}		local p = {}

	local scripts_txt = "some Wikipedia page"		local scripts_txt = 'some Wikipedia page'
	local property_value_aliases_txt = "some Wikipedia page"		local property_value_aliases_txt = 'some Wikipedia page'

			local Array = require 'Module:Array'

	local function pattern_escape(str)		local function pattern_escape(str)
Line 31:		Line 33:
	end })		end })

	local script_ranges = {}		local script_ranges = Array()

	local prev_codepoint, prev_script_name, prev_script_range		local prev_codepoint, prev_script_name, prev_script_range
Line 41:		Line 43:
	else		else
	script_range = { codepoint1, codepoint2 or codepoint1, script_name_to_code[script_name] }		script_range = { codepoint1, codepoint2 or codepoint1, script_name_to_code[script_name] }
	~~table.~~insert(~~script_ranges,~~ script_range)		script_ranges:insert(script_range)
	end		end
	prev_codepoint, prev_script_name, prev_script_range =		prev_codepoint, prev_script_name, prev_script_range =
Line 54:		Line 56:
	if low == high then		if low == high then
	singles[low] = script_code		singles[low] = script_code
	~~table.~~remove(~~script_ranges,~~ i)		script_ranges:remove(i)
	else		else
	i = i + 1		i = i + 1
Line 60:		Line 62:
	end		end

			script_ranges:sort(
	table.sort(script_ranges,
	function (range1, range2)		function (range1, range2)
	return range1[1] < range2[1]		return range1[1] < range2[1]
Line 81:		Line 83:
	]]		]]

	local printed_ranges = {}		local printed_ranges = Array()
	for _, range in ipairs(script_ranges) do		for _, range in ipairs(script_ranges) do
	local low, high, script_code = table.unpack(range)		local low, high, script_code = table.unpack(range)
	~~table.~~insert(~~printed_ranges,~~ ('\t{ 0x%05X, 0x%05X, "%s" },'):format(low, high, script_code))		printed_ranges:insert(('\t{ 0x%05X, 0x%05X, "%s" },'):format(low, high, script_code))
	end		end

	local printed_singles = {}		local printed_singles = Array()
	for codepoint, script_code in require 'Module:~~table~~'.sortedPairs(singles) do		for codepoint, script_code in require 'Module:TableTools'.sortedPairs(singles) do
	~~table.~~insert(~~printed_singles,~~ ('\t[0x%05X] = "%s",'):format(codepoint, script_code))		printed_singles:insert(('\t[0x%05X] = "%s",'):format(codepoint, script_code))
	end		end

	local printed_script_name_to_code = {}		local printed_script_name_to_code = Array()
	for name, code in require 'Module:~~table~~'.sortedPairs(script_name_to_code) do		for name, code in require 'Module:TableTools'.sortedPairs(script_name_to_code) do
	~~table.~~insert(~~printed_script_name_to_code,~~ ('%s = "%s",'):format(code, name:gsub('_', ' ')))		printed_script_name_to_code:insert(('%s = "%s",'):format(code, name:gsub('_', ' ')))
	end		end

	local data = template		local data = template
	:gsub('%.%.%.', ~~table.~~concat(~~printed_ranges,~~ '\n'), 1)		:gsub('%.%.%.', printed_ranges:concat('\n'), 1)
	:gsub('%.%.%.', ~~table.~~concat(~~printed_singles,~~ '\n'), 1)		:gsub('%.%.%.', printed_singles:concat('\n'), 1)
	:gsub('%.%.%.', ~~table.~~concat(~~printed_script_name_to_code,~~ '\n'), 1)		:gsub('%.%.%.', printed_script_name_to_code:concat('\n'), 1)

	return data		return data

Erutuon: consistency

2019-03-11T21:56:59Z

consistency

← Previous revision		Revision as of 21:56, 11 March 2019
Line 47:		Line 47:
	end		end

	local ~~individual~~ = {}		local singles = {}
	local i = 1		local i = 1

Line 53:		Line 53:
	local low, high, script_code = table.unpack(script_ranges[i])		local low, high, script_code = table.unpack(script_ranges[i])
	if low == high then		if low == high then
	~~individual~~[low] = script_code		singles[low] = script_code
	table.remove(script_ranges, i)		table.remove(script_ranges, i)
	else		else
Line 87:		Line 87:
	end		end

	local ~~printed_individual~~ = {}		local printed_singles = {}
	for codepoint, script_code in require 'Module:table'.sortedPairs(~~individual~~) do		for codepoint, script_code in require 'Module:table'.sortedPairs(singles) do
	table.insert(~~printed_individual~~, ('\t[0x%05X] = "%s",'):format(codepoint, script_code))		table.insert(printed_singles, ('\t[0x%05X] = "%s",'):format(codepoint, script_code))
	end		end

Line 99:		Line 99:
	local data = template		local data = template
	:gsub('%.%.%.', table.concat(printed_ranges, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_ranges, '\n'), 1)
	:gsub('%.%.%.', table.concat(~~printed_individual~~, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_singles, '\n'), 1)
	:gsub('%.%.%.', table.concat(printed_script_name_to_code, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_script_name_to_code, '\n'), 1)

Erutuon: wrong variable

2019-03-11T21:56:11Z

wrong variable

← Previous revision		Revision as of 21:56, 11 March 2019
Line 100:		Line 100:
	:gsub('%.%.%.', table.concat(printed_ranges, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_ranges, '\n'), 1)
	:gsub('%.%.%.', table.concat(printed_individual, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_individual, '\n'), 1)
	:gsub('%.%.%.', table.concat(~~printed_individual~~, '\n'), 1)		:gsub('%.%.%.', table.concat(printed_script_name_to_code, '\n'), 1)

	return data		return data

Erutuon: remove detritus

2019-03-11T21:55:28Z

remove detritus

← Previous revision		Revision as of 21:55, 11 March 2019
Line 1:		Line 1:
	local infilehandle = assert(io.open([[./Scripts.txt]], 'rb'))
	local script_data = assert(infilehandle:read 'a')
	infilehandle:close()
	local outfile = [[./data.lua]]

	local script_name_to_code = dofile [[./name_to_code.lua]]

	local p = {}		local p = {}

Erutuon: ←Created page with 'local infilehandle = assert(io.open(./Scripts.txt, 'rb')) local script_data = assert(infilehandle:read 'a') infilehandle:close() local outfile = [[./data.lua...'

2019-03-11T21:55:10Z

←Created page with 'local infilehandle = assert(io.open([[./Scripts.txt]], 'rb')) local script_data = assert(infilehandle:read 'a') infilehandle:close() local outfile = [[./data.lua...'

New page

local infilehandle = assert(io.open([[./Scripts.txt]], 'rb'))
local script_data = assert(infilehandle:read 'a')
infilehandle:close()
local outfile = [[./data.lua]]

local script_name_to_code = dofile [[./name_to_code.lua]]

local p = {}

local scripts_txt = "some Wikipedia page"
local property_value_aliases_txt = "some Wikipedia page"

local function pattern_escape(str)
return (str:gsub('%p', '%%%1'))
end

function p.make_script_name_to_code(page_name)
local content = mw.title.new(page_name):getContent()

local script_aliases = property_value_aliases:match(
pattern_escape '# Script (sc)'
.. '%s+(.-)%s+'
.. pattern_escape '# Script_Extensions (scx)')

local script_name_to_code = {}

for code, name in script_aliases:gmatch 'sc%s+;%s+(%a+)%s+;%s+([%a_]+)' do
script_name_to_code[name] = code
end

return script_name_to_code
end

function p.main(frame)
local script_name_to_code = p.make_script_name_to_code()
setmetatable(script_name_to_code, { __index = function (self, k)
error(('No code for "%s"'):format(k))
end })

local script_ranges = {}

local prev_codepoint, prev_script_name, prev_script_range
for codepoint1, codepoint2, script_name in script_data:gmatch '%f[^\n%z](%x+)%.?%.?(%x*)%s+;%s*([%w_]+)' do
codepoint1, codepoint2 = tonumber(codepoint1, 16), tonumber(codepoint2, 16)
local script_range
if prev_script_range and script_name == prev_script_name and codepoint1 - prev_codepoint == 1 then
prev_script_range[2] = codepoint2 or codepoint1
else
script_range = { codepoint1, codepoint2 or codepoint1, script_name_to_code[script_name] }
table.insert(script_ranges, script_range)
end
prev_codepoint, prev_script_name, prev_script_range =
codepoint2 or codepoint1, script_name, script_range or prev_script_range
end

local individual = {}
local i = 1

while script_ranges[i] do
local low, high, script_code = table.unpack(script_ranges[i])
if low == high then
individual[low] = script_code
table.remove(script_ranges, i)
else
i = i + 1
end
end

table.sort(script_ranges,
function (range1, range2)
return range1[1] < range2[1]
end)

local template = [[
local data = {
singles = {
...
},

ranges = {
...
},
-- Scripts.txt gives full names; here we consider them aliases to save space.
aliases = {
...
},
}
]]

local printed_ranges = {}
for _, range in ipairs(script_ranges) do
local low, high, script_code = table.unpack(range)
table.insert(printed_ranges, ('\t{ 0x%05X, 0x%05X, "%s" },'):format(low, high, script_code))
end

local printed_individual = {}
for codepoint, script_code in require 'Module:table'.sortedPairs(individual) do
table.insert(printed_individual, ('\t[0x%05X] = "%s",'):format(codepoint, script_code))
end

local printed_script_name_to_code = {}
for name, code in require 'Module:table'.sortedPairs(script_name_to_code) do
table.insert(printed_script_name_to_code, ('%s = "%s",'):format(code, name:gsub('_', ' ')))
end

local data = template
:gsub('%.%.%.', table.concat(printed_ranges, '\n'), 1)
:gsub('%.%.%.', table.concat(printed_individual, '\n'), 1)
:gsub('%.%.%.', table.concat(printed_individual, '\n'), 1)

return data
end

return p