Jump to content

Module:TableTools: Difference between revisions

Update from sandbox per request
m (1 revision imported)
 
en>Pppery
(Update from sandbox per request)
Line 1: Line 1:
--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--                               TableTools                                       --
--                                   TableTools                                   --
--                                                                                --
--                                                                                --
-- This module includes a number of functions for dealing with Lua tables.        --
-- This module includes a number of functions for dealing with Lua tables.        --
-- It is a meta-module, meant to be called from other Lua modules, and should     --
-- It is a meta-module, meant to be called from other Lua modules, and should not --
-- not be called directly from #invoke.                                           --
-- be called directly from #invoke.                                               --
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]


local libraryUtil = require('libraryUtil')
local libraryUtil = require('libraryUtil')
Line 19: Line 17:
local checkTypeMulti = libraryUtil.checkTypeMulti
local checkTypeMulti = libraryUtil.checkTypeMulti


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- isPositiveInteger
-- isPositiveInteger
Line 28: Line 25:
-- hash part of a table.
-- hash part of a table.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.isPositiveInteger(v)
function p.isPositiveInteger(v)
return type(v) == 'number' and v >= 1 and floor(v) == v and v < infinity
return type(v) == 'number' and v >= 1 and floor(v) == v and v < infinity
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- isNan
-- isNan
--
--
-- This function returns true if the given number is a NaN value, and false
-- This function returns true if the given number is a NaN value, and false if
-- if not. Although it doesn't operate on tables, it is included here as it is
-- not. Although it doesn't operate on tables, it is included here as it is useful
-- useful for determining whether a value can be a valid table key. Lua will
-- for determining whether a value can be a valid table key. Lua will generate an
-- generate an error if a NaN is used as a table key.
-- error if a NaN is used as a table key.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.isNan(v)
function p.isNan(v)
return type(v) == 'number' and tostring(v) == '-nan'
return type(v) == 'number' and v ~= v
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- shallowClone
-- shallowClone
Line 55: Line 48:
-- table will have no metatable of its own.
-- table will have no metatable of its own.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.shallowClone(t)
function p.shallowClone(t)
checkType('shallowClone', 1, t, 'table')
local ret = {}
local ret = {}
for k, v in pairs(t) do
for k, v in pairs(t) do
Line 64: Line 57:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- removeDuplicates
-- removeDuplicates
Line 72: Line 64:
-- removed, but otherwise the array order is unchanged.
-- removed, but otherwise the array order is unchanged.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.removeDuplicates(arr)
function p.removeDuplicates(t)
checkType('removeDuplicates', 1, arr, 'table')
checkType('removeDuplicates', 1, t, 'table')
local isNan = p.isNan
local isNan = p.isNan
local ret, exists = {}, {}
local ret, exists = {}, {}
for i, v in ipairs(t) do
for _, v in ipairs(arr) do
if isNan(v) then
if isNan(v) then
-- NaNs can't be table keys, and they are also unique, so we don't need to check existence.
-- NaNs can't be table keys, and they are also unique, so we don't need to check existence.
ret[#ret + 1] = v
ret[#ret + 1] = v
else
elseif not exists[v] then
if not exists[v] then
ret[#ret + 1] = v
ret[#ret + 1] = v
exists[v] = true
exists[v] = true
end
end
end
end
end
return ret
return ret
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- numKeys
-- numKeys
Line 98: Line 86:
-- keys that have non-nil values, sorted in numerical order.
-- keys that have non-nil values, sorted in numerical order.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.numKeys(t)
function p.numKeys(t)
checkType('numKeys', 1, t, 'table')
checkType('numKeys', 1, t, 'table')
local isPositiveInteger = p.isPositiveInteger
local isPositiveInteger = p.isPositiveInteger
local nums = {}
local nums = {}
for k, v in pairs(t) do
for k in pairs(t) do
if isPositiveInteger(k) then
if isPositiveInteger(k) then
nums[#nums + 1] = k
nums[#nums + 1] = k
Line 112: Line 99:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- affixNums
-- affixNums
Line 118: Line 104:
-- This takes a table and returns an array containing the numbers of keys with the
-- This takes a table and returns an array containing the numbers of keys with the
-- specified prefix and suffix. For example, for the table
-- specified prefix and suffix. For example, for the table
-- {a1 = 'foo', a3 = 'bar', a6 = 'baz'} and the prefix "a", affixNums will
-- {a1 = 'foo', a3 = 'bar', a6 = 'baz'} and the prefix "a", affixNums will return
-- return {1, 3, 6}.
-- {1, 3, 6}.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.affixNums(t, prefix, suffix)
function p.affixNums(t, prefix, suffix)
checkType('affixNums', 1, t, 'table')
checkType('affixNums', 1, t, 'table')
Line 129: Line 114:
local function cleanPattern(s)
local function cleanPattern(s)
-- Cleans a pattern so that the magic characters ()%.[]*+-?^$ are interpreted literally.
-- Cleans a pattern so that the magic characters ()%.[]*+-?^$ are interpreted literally.
s = s:gsub('([%(%)%%%.%[%]%*%+%-%?%^%$])', '%%%1')
return s:gsub('([%(%)%%%.%[%]%*%+%-%?%^%$])', '%%%1')
return s
end
end


Line 140: Line 124:


local nums = {}
local nums = {}
for k, v in pairs(t) do
for k in pairs(t) do
if type(k) == 'string' then
if type(k) == 'string' then
local num = mw.ustring.match(k, pattern)
local num = mw.ustring.match(k, pattern)
if num then
if num then
Line 152: Line 136:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- numData
-- numData
--
--
-- Given a table with keys like ("foo1", "bar1", "foo2", "baz2"), returns a table
-- Given a table with keys like {"foo1", "bar1", "foo2", "baz2"}, returns a table
-- of subtables in the format  
-- of subtables in the format
-- { [1] = {foo = 'text', bar = 'text'}, [2] = {foo = 'text', baz = 'text'} }
-- {[1] = {foo = 'text', bar = 'text'}, [2] = {foo = 'text', baz = 'text'}}.
-- Keys that don't end with an integer are stored in a subtable named "other".
-- Keys that don't end with an integer are stored in a subtable named "other". The
-- The compress option compresses the table so that it can be iterated over with
-- compress option compresses the table so that it can be iterated over with
-- ipairs.
-- ipairs.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.numData(t, compress)
function p.numData(t, compress)
checkType('numData', 1, t, 'table')
checkType('numData', 1, t, 'table')
Line 193: Line 175:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- compressSparseArray
-- compressSparseArray
Line 201: Line 182:
-- ipairs.
-- ipairs.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.compressSparseArray(t)
function p.compressSparseArray(t)
checkType('compressSparseArray', 1, t, 'table')
checkType('compressSparseArray', 1, t, 'table')
Line 212: Line 192:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- sparseIpairs
-- sparseIpairs
Line 219: Line 198:
-- handle nil values.
-- handle nil values.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.sparseIpairs(t)
function p.sparseIpairs(t)
checkType('sparseIpairs', 1, t, 'table')
checkType('sparseIpairs', 1, t, 'table')
Line 236: Line 214:
end
end


--[[
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
-- size
-- size
Line 243: Line 220:
-- but for arrays it is more efficient to use the # operator.
-- but for arrays it is more efficient to use the # operator.
------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
--]]
function p.size(t)
function p.size(t)
checkType('size', 1, t, 'table')
checkType('size', 1, t, 'table')
local i = 0
local i = 0
for k in pairs(t) do
for _ in pairs(t) do
i = i + 1
i = i + 1
end
end
return i
return i
end
end


local function defaultKeySort(item1, item2)
local function defaultKeySort(item1, item2)
Line 260: Line 234:
if type1 ~= type2 then
if type1 ~= type2 then
return type1 < type2
return type1 < type2
else -- This will fail with table, boolean, function.
elseif type1 == 'table' or type1 == 'boolean' or type1 == 'function' then
return tostring(item1) < tostring(item2)
else
return item1 < item2
return item1 < item2
end
end
end
end
 
------------------------------------------------------------------------------------
--[[
-- keysToList
Returns a list of the keys in a table, sorted using either a default
--
comparison function or a custom keySort function.
-- Returns an array of the keys in a table, sorted using either a default
]]
-- comparison function or a custom keySort function.
------------------------------------------------------------------------------------
function p.keysToList(t, keySort, checked)
function p.keysToList(t, keySort, checked)
if not checked then
if not checked then
checkType('keysToList', 1, t, 'table')
checkType('keysToList', 1, t, 'table')
checkTypeMulti('keysToList', 2, keySort, { 'function', 'boolean', 'nil' })
checkTypeMulti('keysToList', 2, keySort, {'function', 'boolean', 'nil'})
end
end
 
local list = {}
local arr = {}
local index = 1
local index = 1
for key, value in pairs(t) do
for k in pairs(t) do
list[index] = key
arr[index] = k
index = index + 1
index = index + 1
end
end
 
if keySort ~= false then
if keySort ~= false then
keySort = type(keySort) == 'function' and keySort or defaultKeySort
keySort = type(keySort) == 'function' and keySort or defaultKeySort
table.sort(arr, keySort)
table.sort(list, keySort)
end
end
 
return list
return arr
end
end


--[[
------------------------------------------------------------------------------------
Iterates through a table, with the keys sorted using the keysToList function.
-- sortedPairs
If there are only numerical keys, sparseIpairs is probably more efficient.
--
]]
-- Iterates through a table, with the keys sorted using the keysToList function.
-- If there are only numerical keys, sparseIpairs is probably more efficient.
------------------------------------------------------------------------------------
function p.sortedPairs(t, keySort)
function p.sortedPairs(t, keySort)
checkType('sortedPairs', 1, t, 'table')
checkType('sortedPairs', 1, t, 'table')
checkType('sortedPairs', 2, keySort, 'function', true)
checkType('sortedPairs', 2, keySort, 'function', true)
 
local list = p.keysToList(t, keySort, true)
local arr = p.keysToList(t, keySort, true)
 
local i = 0
local i = 0
return function()
return function ()
i = i + 1
i = i + 1
local key = list[i]
local key = arr[i]
if key ~= nil then
if key ~= nil then
return key, t[key]
return key, t[key]
Line 313: Line 291:
end
end


--[[
------------------------------------------------------------------------------------
Returns true if all keys in the table are consecutive integers starting at 1.
-- isArray
--]]
--
function p.isArray(t)
-- Returns true if the given value is a table and all keys are consecutive
checkType("isArray", 1, t, "table")
-- integers starting at 1.
------------------------------------------------------------------------------------
function p.isArray(v)
if type(v) ~= 'table' then
return false
end
local i = 0
for _ in pairs(v) do
i = i + 1
if v[i] == nil then
return false
end
end
return true
end
 
------------------------------------------------------------------------------------
-- isArrayLike
--
-- Returns true if the given value is iterable and all keys are consecutive
-- integers starting at 1.
------------------------------------------------------------------------------------
function p.isArrayLike(v)
if not pcall(pairs, v) then
return false
end
local i = 0
local i = 0
for k, v in pairs(t) do
for _ in pairs(v) do
i = i + 1
i = i + 1
if t[i] == nil then
if v[i] == nil then
return false
return false
end
end
Line 329: Line 331:
end
end


-- { "a", "b", "c" } -> { a = 1, b = 2, c = 3 }
------------------------------------------------------------------------------------
function p.invert(array)
-- invert
checkType("invert", 1, array, "table")
--
-- Transposes the keys and values in an array. For example, {"a", "b", "c"} ->
-- {a = 1, b = 2, c = 3}. Duplicates are not supported (result values refer to
-- the index of the last duplicate) and NaN values are ignored.
------------------------------------------------------------------------------------
function p.invert(arr)
checkType("invert", 1, arr, "table")
local isNan = p.isNan
local map = {}
local map = {}
for i, v in ipairs(array) do
for i, v in ipairs(arr) do
map[v] = i
if not isNan(v) then
map[v] = i
end
end
end
 
return map
return map
end
end


--[[
------------------------------------------------------------------------------------
{ "a", "b", "c" } -> { ["a"] = true, ["b"] = true, ["c"] = true }
-- listToSet
--]]
--
function p.listToSet(t)
-- Creates a set from the array part of the table. Indexing the set by any of the
checkType("listToSet", 1, t, "table")
-- values of the array returns true. For example, {"a", "b", "c"} ->
-- {a = true, b = true, c = true}. NaN values are ignored as Lua considers them
-- never equal to any value (including other NaNs or even themselves).
------------------------------------------------------------------------------------
function p.listToSet(arr)
checkType("listToSet", 1, arr, "table")
local isNan = p.isNan
local set = {}
local set = {}
for _, item in ipairs(t) do
for _, v in ipairs(arr) do
set[item] = true
if not isNan(v) then
set[v] = true
end
end
end
 
return set
return set
end
end


--[[
------------------------------------------------------------------------------------
Recursive deep copy function.
-- deepCopy
Preserves identities of subtables.
--
-- Recursive deep copy function. Preserves identities of subtables.
]]
------------------------------------------------------------------------------------
local function _deepCopy(orig, includeMetatable, already_seen)
local function _deepCopy(orig, includeMetatable, already_seen)
-- Stores copies of tables indexed by the original table.
if type(orig) ~= "table" then
already_seen = already_seen or {}
return orig
end
-- already_seen stores copies of tables indexed by the original table.
local copy = already_seen[orig]
local copy = already_seen[orig]
if copy ~= nil then
if copy ~= nil then
Line 369: Line 388:
end
end
if type(orig) == 'table' then
copy = {}
copy = {}
already_seen[orig] = copy -- memoize before any recursion, to avoid infinite loops
for orig_key, orig_value in pairs(orig) do
copy[deepcopy(orig_key, includeMetatable, already_seen)] = deepcopy(orig_value, includeMetatable, already_seen)
for orig_key, orig_value in pairs(orig) do
copy[_deepCopy(orig_key, includeMetatable, already_seen)] = _deepCopy(orig_value, includeMetatable, already_seen)
end
if includeMetatable then
local mt = getmetatable(orig)
if mt ~= nil then
setmetatable(copy, _deepCopy(mt, true, already_seen))
end
end
already_seen[orig] = copy
if includeMetatable then
local mt = getmetatable(orig)
if mt ~= nil then
local mt_copy = deepcopy(mt, includeMetatable, already_seen)
setmetatable(copy, mt_copy)
already_seen[mt] = mt_copy
end
end
else -- number, string, boolean, etc
copy = orig
end
end
return copy
return copy
end
end
Line 392: Line 407:
function p.deepCopy(orig, noMetatable, already_seen)
function p.deepCopy(orig, noMetatable, already_seen)
checkType("deepCopy", 3, already_seen, "table", true)
checkType("deepCopy", 3, already_seen, "table", true)
return _deepCopy(orig, not noMetatable, already_seen or {})
return _deepCopy(orig, not noMetatable, already_seen)
end
end


--[[
------------------------------------------------------------------------------------
Concatenates all values in the table that are indexed by a number, in order.
-- sparseConcat
sparseConcat{ a, nil, c, d }  =>  "acd"
--
sparseConcat{ nil, b, c, d }  =>  "bcd"
-- Concatenates all values in the table that are indexed by a number, in order.
]]
-- sparseConcat{a, nil, c, d}  =>  "acd"
-- sparseConcat{nil, b, c, d}  =>  "bcd"
------------------------------------------------------------------------------------
function p.sparseConcat(t, sep, i, j)
function p.sparseConcat(t, sep, i, j)
local list = {}
local arr = {}
 
local list_i = 0
local arr_i = 0
for _, v in p.sparseIpairs(t) do
for _, v in p.sparseIpairs(t) do
list_i = list_i + 1
arr_i = arr_i + 1
list[list_i] = v
arr[arr_i] = v
end
end
 
return table.concat(list, sep, i, j)
return table.concat(arr, sep, i, j)
end
end


--[[
------------------------------------------------------------------------------------
-- Finds the length of an array, or of a quasi-array with keys such
-- length
-- as "data1", "data2", etc., using an exponental search algorithm.  
--
-- It is similar to the operator #, but may return
-- Finds the length of an array, or of a quasi-array with keys such as "data1",
-- a different value when there are gaps in the array portion of the table.
-- "data2", etc., using an exponential search algorithm. It is similar to the
-- Intended to be used on data loaded with mw.loadData. For other tables, use #.
-- operator #, but may return a different value when there are gaps in the array
-- Note: #frame.args in frame object always be set to 0, regardless of  
-- portion of the table. Intended to be used on data loaded with mw.loadData. For
-- the number of unnamed template parameters, so use this function for
-- other tables, use #.
-- frame.args.
-- Note: #frame.args in frame object always be set to 0, regardless of the number
--]]
-- of unnamed template parameters, so use this function for frame.args.
 
------------------------------------------------------------------------------------
function p.length(t, prefix)
function p.length(t, prefix)
-- requiring module inline so that [[Module:Exponental search]]
-- requiring module inline so that [[Module:Exponential search]] which is
-- which is only needed by this one function
-- only needed by this one function doesn't get millions of transclusions
-- doesn't get millions of transclusions
local expSearch = require("Module:Exponential search")
local expSearch = require("Module:Exponential search")
checkType('length', 1, t, 'table')
checkType('length', 1, t, 'table')
checkType('length', 2, prefix, 'string', true)
checkType('length', 2, prefix, 'string', true)
return expSearch(function(i)
return expSearch(function (i)
local key
local key
if prefix then
if prefix then
Line 441: Line 456:
end) or 0
end) or 0
end
end
------------------------------------------------------------------------------------
-- inArray
--
-- Returns true if valueToFind is a member of the array, and false otherwise.
------------------------------------------------------------------------------------
function p.inArray(arr, valueToFind)
function p.inArray(arr, valueToFind)
checkType("inArray", 1, arr, "table")
checkType("inArray", 1, arr, "table")
-- if valueToFind is nil, error?
-- if valueToFind is nil, error?
 
for _, v in ipairs(arr) do
for _, v in ipairs(arr) do
if v == valueToFind then
if v == valueToFind then
Line 451: Line 471:
end
end
end
end
return false
return false
end
------------------------------------------------------------------------------------
-- merge
--
-- Given the arrays, returns an array containing the elements of each input array
-- in sequence.
------------------------------------------------------------------------------------
function p.merge(...)
local arrays = {...}
local ret = {}
for i, arr in ipairs(arrays) do
checkType('merge', i, arr, 'table')
for _, v in ipairs(arr) do
ret[#ret + 1] = v
end
end
return ret
end
------------------------------------------------------------------------------------
-- extend
--
-- Extends the first array in place by appending all elements from the second
-- array.
------------------------------------------------------------------------------------
function p.extend(arr1, arr2)
checkType('extend', 1, arr1, 'table')
checkType('extend', 2, arr2, 'table')
for _, v in ipairs(arr2) do
arr1[#arr1 + 1] = v
end
end
end


return p
return p
Anonymous user