မဝ်ဂျူ:string/templates

Documentation for this module may be created at မဝ်ဂျူ:string/templates/doc

local str = {}

local parameters_module = "Module:parameters"
local patterns_module = "Module:patterns"
local string_utilities_module = "Module:string utilities"

local abs = math.abs
local find = string.find
local format = string.format
local floor = math.floor
local loader = package.loaders[2]
local lower = string.lower
local match = string.match
local rep = string.rep
local require = require
local select = select
local tonumber = tonumber
local type = type
local unpack = unpack

local function decode_uri(...)
	decode_uri = require(string_utilities_module).decode_uri
	return decode_uri(...)
end

local function pattern_escape(...)
	pattern_escape = require(patterns_module).pattern_escape
	return pattern_escape(...)
end

local function process_params(...)
	process_params = require(parameters_module).process
	return process_params(...)
end

local function replacement_escape(...)
	replacement_escape = require(patterns_module).replacement_escape
	return replacement_escape(...)
end

local function ufind(...)
	ufind = require(string_utilities_module).find
	return ufind(...)
end

local function ugmatch(...)
	ugmatch = require(string_utilities_module).gmatch
	return ugmatch(...)
end

local function ugsub(...)
	ugsub = require(string_utilities_module).gsub
	return ugsub(...)
end

local function ulen(...)
	ulen = require(string_utilities_module).len
	return ulen(...)
end

local function ulower(...)
	ulower = require(string_utilities_module).lower
	return ulower(...)
end

local function umatch(...)
	umatch = require(string_utilities_module).match
	return umatch(...)
end

local function usub(...)
	usub = require(string_utilities_module).sub
	return usub(...)
end

--[[
Helper function that populates the argument list given that user may need to use a mix of
named and unnamed parameters.  This is relevant because named parameters are not
identical to unnamed parameters due to string trimming, and when dealing with strings
we sometimes want to either preserve or remove that whitespace depending on the application.
]]
local function _getParameters(frame_args, arg_list)
	local new_args, i, value = {}, 1
	
	for _, arg in ipairs(arg_list) do
		value = frame_args[arg]
		if value == nil then
			value = frame_args[i]
			i = i + 1
		end
		new_args[arg] = value
	end
	
	return new_args
end

--[[
len

This function returns the length of the target string.

Usage:
{{#invoke:string/templates|len|target_string|}}
OR
{{#invoke:string/templates|len|s=target_string}}

Parameters
    s: The string whose length to report

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the target string.
]]
function str.len(frame)
	return ulen(_getParameters(frame.args, {"s"}).s or "")
end

--[[
len_visible

This function returns the length of the target string, excluding the text encompassed in < ... >

Usage: exactly as len, above.
]]
function str.len_visible(frame)
	return ulen(ugsub(_getParameters(frame.args, {"s"}).s or "", "<[^<>]+>", ""))
end

--[[
sub

This function returns a substring of the target string at specified indices.

Usage:
{{#invoke:string/templates|sub|target_string|start_index|end_index}}
OR
{{#invoke:string/templates|sub|s=target_string|i=start_index|j=end_index}}

Parameters
    s: The string to return a subset of
    i: The first index of the substring to return, defaults to 1.
    j: The last index of the string to return, defaults to the last character.
    
The first character of the string is assigned an index of 1.  If either i or j
is a negative value, it is interpreted the same as selecting a character by
counting from the end of the string.  Hence, a value of -1 is the same as
selecting the last character of the string.

If the requested indices are out of range for the given string, an error is
reported.
]]
function str.sub(frame)
	local new_args = _getParameters(frame.args, {"s", "i", "j"})
	local s = new_args["s"] or ""
	local i = tonumber(new_args["i"]) or 1
	local j = tonumber(new_args["j"]) or -1
	
	local s_len = ulen(s)
	
	-- Convert negatives for range checking
	if i < 0 then
		i = s_len + i + 1
	end
	if j < 0 then
		j = s_len + j + 1
	end
	
	if i > s_len or j > s_len then
		return str._error('String subset index out of range')
	elseif j < i then
		return str._error('String subset indices out of order')
	end
	return usub(s, i, j)
end

--[[
This function implements that features of {{str sub old}} and is kept in order
to maintain these older templates.
]]
function str.sublength(frame)
	local i = tonumber(frame.args.i) or 0
	local len = tonumber(frame.args.len)
	return usub(frame.args.s, i + 1, len and (i + len))
end

--[[
match

This function returns a substring from the source string that matches a
specified pattern.

Usage:
{{#invoke:string/templates|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}
OR
{{#invoke:string/templates|pos|s=source_string|pattern=pattern_string|start=start_index
    |match=match_number|plain=plain_flag|nomatch=nomatch_output}}

Parameters
    s: The string to search
    pattern: The pattern or string to find within the string
    start: The index within the source string to start the search.  The first
        character of the string has index 1.  Defaults to 1.
    match: In some cases it may be possible to make multiple matches on a single
        string.  This specifies which match to return, where the first match is
        match= 1.  If a negative number is specified then a match is returned
        counting from the last match.  Hence match = -1 is the same as requesting
        the last match.  Defaults to 1.
    plain: A flag indicating that the pattern should be understood as plain
        text.  Defaults to false.
    nomatch: If no match is found, output the "nomatch" value rather than an error.

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from each string.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.

If the match_number or start_index are out of range for the string being queried, then
this function generates an error.  An error is also generated if no match is found.
If one adds the parameter ignore_errors=true, then the error will be suppressed and
an empty string will be returned on any failure.

For information on constructing Lua patterns, a form of [regular expression], see:

* http://www.lua.org/manual/5.1/manual.html#5.4.1
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns

]]
function str.match(frame)
	local new_args = _getParameters(frame.args, { 's', 'pattern', 'start', 'match', 'plain', 'nomatch' })
	local s = new_args['s'] or ''
	local start = tonumber(new_args['start']) or 1
	local plain_flag = str._getBoolean(new_args['plain'] or false)
	local pattern = new_args['pattern'] or ''
	local match_index = floor(tonumber(new_args['match']) or 1)
	local nomatch = new_args['nomatch']
	
	if s == '' then
		return str._error('Target string is empty')
	elseif pattern == '' then
		return str._error('Pattern string is empty')
	elseif abs(start) < 1 or abs(start) > ulen(s) then
		return str._error('Requested start is out of range')
	elseif match_index == 0 then
		return str._error('Match index is out of range')
	elseif plain_flag then
		pattern = pattern_escape(pattern)
	end
	
	local result
	if match_index == 1 then
		-- Find first match is simple case
		result = umatch(s, pattern, start)
	else
		if start > 1 then
			s = usub(s, start)
		end
		
		local iterator = ugmatch(s, pattern)
		if match_index > 0 then
			-- Forward search
			for w in iterator do
				match_index = match_index - 1
				if match_index == 0 then
					result = w
					break
				end
			end
		else
			-- Reverse search
			local result_table, i = {}, 0
			for w in iterator do
				i = i + 1
				result_table[i] = w
			end
			
			result = result_table[i + match_index]
		end
	end
	
	if result ~= nil then
		return result
	elseif nomatch == nil then
		return str._error('Match not found')
	end
	return nomatch
end

--[[
pos

This function returns a single character from the target string at position pos.

Usage:
{{#invoke:string/templates|pos|target_string|index_value}}
OR
{{#invoke:string/templates|pos|target=target_string|pos=index_value}}

Parameters
    target: The string to search
    pos: The index for the character to return

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the target string.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.

The first character has an index value of 1.

If one requests a negative value, this function will select a character by counting backwards
from the end of the string.  In other words pos = -1 is the same as asking for the last character.

A requested value of zero, or a value greater than the length of the string returns an error.
]]
function str.pos(frame)
	local new_args = _getParameters(frame.args, { 'target', 'pos' })
	local target_str = new_args['target'] or ''
	local pos = tonumber(new_args['pos']) or 0
	
	if pos == 0 or abs(pos) > ulen(target_str) then
		return str._error('String index out of range')
	end
	
	return usub(target_str, pos, pos)
end

--[[
str_find

This function duplicates the behavior of {{str_find}}, including all of its quirks.
This is provided in order to support existing templates, but is NOT RECOMMENDED for
new code and templates.  New code is recommended to use the "find" function instead.

Returns the first index in "source" that is a match to "target".  Indexing is 1-based,
and the function returns -1 if the "target" string is not present in "source".

Important Note: If the "target" string is empty / missing, this function returns a
value of "1", which is generally unexpected behavior, and must be accounted for
separatetly.
]]
function str.str_find(frame)
	local new_args = _getParameters(frame.args, { 'source', 'target' })
	local source_str = new_args['source'] or ''
	local target_str = new_args['target'] or ''
	
	if target_str == '' then
		return 1
	end
	
	local start = ufind(source_str, target_str, 1, true)
	if start == nil then
		start = -1
	end
	
	return start
end

--[[
find

This function allows one to search for a target string or pattern within another
string.

Usage:
{{#invoke:string/templates|find|source_str|target_string|start_index|plain_flag}}
OR
{{#invoke:string/templates|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}

Parameters
    source: The string to search
    target: The string or pattern to find within source
    start: The index within the source string to start the search, defaults to 1
    plain: Boolean flag indicating that target should be understood as plain
        text and not as a Lua style regular expression, defaults to true

If invoked using named parameters, Mediawiki will automatically remove any leading or
trailing whitespace from the parameter.  In some circumstances this is desirable, in
other cases one may want to preserve the whitespace.

This function returns the first index >= "start" where "target" can be found
within "source".  Indices are 1-based.  If "target" is not found, then this
function returns an empty string.  If either "source" or "target" are missing / empty, this
function also returns an empty string.

This function should be safe for UTF-8 strings.
]]
function str.find(frame)
	local main_param = {required = true, allow_empty = true}
	return ufind(unpack(process_params(frame.args, {
		[1] = main_param,
		[2] = main_param,
		[3] = {type = "number"},
		[4] = {type = "boolean"},
	})))
end

--[[
replace

This function allows one to replace a target string or pattern within another
string.

Usage:
{{#invoke:string/templates|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}
OR
{{#invoke:string/templates|replace|source=source_string|pattern=pattern_string|replace=replace_string|
   count=replacement_count|plain=plain_flag}}

Parameters
    source: The string to search
    pattern: The string or pattern to find within source
    replace: The replacement text
    count: The number of occurences to replace, defaults to all.
    plain: Boolean flag indicating that pattern should be understood as plain
        text and not as a Lua style regular expression, defaults to true
]]
function str.replace(frame)
	local new_args = _getParameters(frame.args, { 'source', 'pattern', 'replace', 'count', 'plain' })
	local source_str = new_args['source'] or ''
	local pattern = new_args['pattern'] or ''
	local replace = new_args['replace'] or ''
	local count = tonumber(new_args['count'])
	local plain = new_args['plain'] or true
	
	if source_str == '' or pattern == '' then
		return source_str
	end
	plain = str._getBoolean(plain)
	
	if plain then
		pattern = pattern_escape(pattern)
		replace = replacement_escape(replace)
	end
	
	return (ugsub(source_str, pattern, replace, count))
end


function str.gsub(frame)
	local main_param = {required = true, allow_empty = true, no_trim = true}
	return (ugsub(unpack(process_params(frame.args, {
		[1] = main_param,
		[2] = main_param,
		[3] = main_param,
		[4] = {type = "number"},
	}))))
end


--[[
    simple function to pipe string.rep to templates.
]]

function str.rep(frame)
	local repetitions = tonumber(frame.args[2])
	if not repetitions then
		return str._error('function rep expects a number as second parameter, received "' .. (frame.args[2] or '') .. '"')
	end
	return rep(frame.args[1] or '', repetitions)
end

function str.lower(frame)
	return ulower(frame.args[1] or "")
end
str.lc = str.lower

--[[
format

This function allows one to format strings according to a template. This is a direct interface onto
str.format() in Lua, and works like the C printf() function.

For example:
{{#invoke:string/templates|format|page_%04d.html|65}}
will produce the result
page_0065.html

Parameters
    1: The format template. See https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#string.format
    2, 3, ...: Arguments to be inserted into the template.

Note that leading and trailing whitespace is not removed from the arguments.
]]
function str.format(frame)
	local fmt = frame.args[1]
	-- You can't call unpack() directly on frame.args because it isn't really a
	-- table, and doesn't support the # operator.
	local args = {}
	local i = 2
	while true do
		local val = frame.args[i]
		if not val then
			break
		end
		table.insert(args, val)
		i = i + 1
	end
	return format(fmt, unpack(args))
end

--[[
Helper function to handle error messages.
]]
function str._error(error_str)
	local frame = mw.getCurrentFrame()
	local error_category = frame.args.error_category or 'Errors reported by Module String Templates'
	local ignore_errors = frame.args.ignore_errors or false
	local no_category = frame.args.no_category or false
	
	if str._getBoolean(ignore_errors) then
		return ''
	end
	
	local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>'
	if error_category ~= '' and not str._getBoolean(no_category) then
		error_str = '[[Category:' .. error_category .. ']]' .. error_str
	end
	
	return error_str
end

--[[
Helper Function to interpret boolean strings
]]
function str._getBoolean(boolean_str)
	local boolean_str_type = type(boolean_str)
	if boolean_str_type == 'boolean' then
		return boolean_str
	elseif boolean_str_type ~= "string" then
		error('No boolean value found')
	end
	boolean_str = lower(boolean_str)
	return not (
		boolean_str == 'false' or
		boolean_str == 'no' or
		boolean_str == '0' or
		boolean_str == ''
	)
end

function str.count(text, pattern, plain)
	if not (type(text) == "string" or type(text) == "number") then
		error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.')
	elseif not (type(pattern) == "string" or type(pattern) == "number") then
		error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.')
	elseif plain then
		pattern = pattern_escape(pattern)
	end
	
	return select(2, ugsub(text, pattern, ""))
end

function str.matchToArray(text, pattern)
	local invoked = false
	
	if type(text) == "table" then
		invoked = true
		
		if text.args then
			local frame = text
			
			local params = {
				[1] = { required = true },
				[2] = { required = true },
			}
			
			local args = process_params(frame.args, params)
			
			text = args[1]
			pattern = args[2]
		else
			error("If the first argument to matchToArray is a table, it should be a frame object.")
		end
	else
		if not (type(pattern) == "string" or type(pattern) == "number") then
			error("The second argument to matchToArray should be a string or a number.")
		end
	end
	
	local matches = {}
	local i = 0
	for match in ugmatch(text, pattern) do
		i = i + 1
		matches[i] = match
	end
	
	if i > 0 then
		if invoked then
			return table.concat(matches, ", ")
		else
			return matches
		end
	else
		if invoked then
			return ""
		else
			return nil
		end
	end
end

--[=[
	Similar to gmatch, but it returns the count of the match in addition to the
	list of captures, something like ipairs().
	
	If the pattern doesn't contain any captures, the whole match is returned.
	
	Invoke thus:
	
		for i, whole_match in require("Module:string/templates").imatch(text, pattern) do
			[ do something with i and whole_match ]
		end
	
	or
	
		for i, capture1[, capture2[, capture3[, ...]]] in require("Module:string/templates").imatch(text, pattern) do
			[ do something with i and capture1 ]
		end
	
	For example, this code
		for i, whole_match in require("Module:string/templates").imatch("a b c", "[a-z]") do
			mw.log(i, whole_match)
		end
	will log
		1	a
		2	b
		3	c
]=]
function str.imatch(text, pattern, pos, plain, use_basic_Lua_function)
	local i = 0
	pos = pos or 0
	if not match(pattern, "%b()") then
		pattern = "(" .. pattern .. ")"
	end
	local _find = use_basic_Lua_function and find or ufind
	return function()
		i = i + 1
		local return_values = { _find(text, pattern, pos, plain) }
		local j = return_values[2]
		
		if return_values[3] then
			pos = j + 1
			-- Skip the first two returned values, which are the indices of the
			-- whole match.
			return i, unpack(return_values, 3)
		end
	end
end

function str.URIdecode(frame)
	return decode_uri(frame.args[1], frame.args[2] or "PATH")
end

function str:__index(k)
	self[k] = loader("Module:string/" .. k)()
	return self[k]
end

return setmetatable(str, str)