Wikipedia

Module:TableTools: Difference between revisions

Browse history interactively
← Previous edit
Content deleted Content added
add isNan function, shallowClone function and removeDuplicates function, fix up valueIntersection function to work properly for NaNs
Update from sandbox per request
 
(21 intermediate revisions by 6 users not shown)
Line 1:
--[[
------------------------------------------------------------------------------------
-- TableTools TableTools --
-- --
-- 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 not --
-- not be called directly from #invoke. --
------------------------------------------------------------------------------------
--]]
 
local libraryUtil = require('libraryUtil')
Line 17 ⟶ 15:
local infinity = math.huge
local checkType = libraryUtil.checkType
local checkTypeMulti = libraryUtil.checkTypeMulti
 
-- Define a unique value to represent NaN. This is because NaN cannot be used as a table key.
local nan = {}
 
--[[
------------------------------------------------------------------------------------
-- isPositiveInteger
Line 30 ⟶ 25:
-- hash part of a table.
------------------------------------------------------------------------------------
--]]
function p.isPositiveInteger(v)
ifreturn type(v) == 'number' and v >= 1 and floor(v) == v and v < infinity then
return true
else
return false
end
end
 
--[[
------------------------------------------------------------------------------------
-- isNan
--
-- 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 useful
-- useful 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.
------------------------------------------------------------------------------------
--]]
function p.isNan(v)
ifreturn type(v) == 'number' and tostring(v) =~= '-nan' thenv
return true
else
return false
end
end
 
--[[
------------------------------------------------------------------------------------
-- shallowClone
Line 65 ⟶ 48:
-- table will have no metatable of its own.
------------------------------------------------------------------------------------
--]]
function p.shallowClone(t)
checkType('shallowClone', 1, t, 'table')
local ret = {}
for k, v in pairs(t) do
Line 74 ⟶ 57:
end
 
--[[
------------------------------------------------------------------------------------
-- removeDuplicates
Line 82 ⟶ 64:
-- removed, but otherwise the array order is unchanged.
------------------------------------------------------------------------------------
function p.removeDuplicates(arr)
--]]
checkType('removeDuplicates', 1, arr, 'table')
function p.removeDuplicates(t)
local isNan = p.isNan
local ret, exists = {}, {}
for i_, v in ipairs(tarr) do
if isNan(v) then
-- NaNs can't be table keys, and they are also unique, so we don't need to check existence.
ret[#ret + 1] = v
elseif not exists[v] then
else
if not exists[v] then
ret[#ret + 1] = v
exists[v] = true
end
end
end
return ret
end
 
--[[
------------------------------------------------------------------------------------
-- union
--
-- This returns the union of the key/value pairs of n tables. If any of the tables
-- contain different values for the same table key, the table value is converted
-- to an array holding all of the different values.
------------------------------------------------------------------------------------
--]]
function p.union(...)
local lim = select('#', ...)
if lim == 0 then
error("no arguments passed to 'union'", 2)
end
local ret, trackArrays = {}, {}
for i = 1, lim do
local t = select(i, ...)
checkType('union', i, t, 'table')
for k, v in pairs(t) do
local retKey = ret[k]
if retKey == nil then
ret[k] = v
elseif retKey ~= v then
if trackArrays[k] then
local array = ret[k]
local valExists
for _, arrayVal in ipairs(array) do
if arrayVal == v then
valExists = true
break
end
end
if not valExists then
array[#array + 1] = v
ret[k] = array
end
else
ret[k] = {ret[k], v}
trackArrays[k] = true
end
end
end
end
return ret
end
 
--[[
------------------------------------------------------------------------------------
-- valueUnion
--
-- This returns the union of the values of n tables, as an array. For example, for
-- the tables {1, 3, 4, 5, foo = 7} and {2, bar = 3, 5, 6}, union will return
-- {1, 2, 3, 4, 5, 6, 7}.
------------------------------------------------------------------------------------
--]]
function p.valueUnion(...)
local lim = select('#', ...)
if lim == 0 then
error("no arguments passed to 'valueUnion'", 2)
end
local vals, ret = {}, {}
for i = 1, lim do
local t = select(i, ...)
checkType('valueUnion', i, t, 'table')
for k, v in pairs(t) do
if type(v) == 'number' and tostring(v) == '-nan' then
v = nan -- NaN cannot be a table key, so use a proxy variable.
end
vals[v] = true
end
end
for val in pairs(vals) do
if val == nan then
-- This ensures that we output a NaN when we had one as input, although
-- they may have been generated in a completely different way.
val = 0/0
end
ret[#ret + 1] = val
end
return ret
end
 
--[[
------------------------------------------------------------------------------------
-- intersection
--
-- This returns the intersection of the key/value pairs of n tables. Both the key
-- and the value must match to be included in the resulting table.
------------------------------------------------------------------------------------
--]]
function p.intersection(...)
local lim = select('#', ...)
if lim == 0 then
error("no arguments passed to 'intersection'", 2)
end
local ret, track, pairCounts = {}, {}, {}
for i = 1, lim do
local t = select(i, ...)
checkType('intersection', i, t, 'table')
for k, v in pairs(t) do
local trackVal = track[k]
if trackVal == nil then
track[k] = v
pairCounts[k] = 1
elseif trackVal == v then
pairCounts[k] = pairCounts[k] + 1
end
end
end
for k, v in pairs(track) do
if pairCounts[k] == lim then
ret[k] = v
end
end
return ret
end
 
--[[
------------------------------------------------------------------------------------
-- valueIntersection
--
-- This returns the intersection of the values of n tables, as an array. For
-- example, for the tables {1, 3, 4, 5, foo = 7} and {2, bar = 3, 5, 6},
-- intersection will return {3, 5}.
------------------------------------------------------------------------------------
--]]
function p.valueIntersection(...)
local lim = select('#', ...)
if lim < 2 then
error(lim .. ' argument' .. (lim == 1 and '' or 's') .. " passed to 'intersection' (minimum is 2)", 2)
end
local isNan = p.isNan
local vals, ret = {}, {}
local isSameTable = true -- Tracks table equality.
local tableTemp -- Used to store the table from the previous loop so that we can check table equality.
for i = 1, lim do
local t = select(i, ...)
checkType('valueIntersection', i, t, 'table')
if tableTemp and t ~= tableTemp then
isSameTable = false
end
tableTemp = t
for k, v in pairs(t) do
-- NaNs are never equal to any other value, so they can't be in the intersection.
-- Which is lucky, as they also can't be table keys.
if not isNan(v) then
local valCount = vals[v] or 0
vals[v] = valCount + 1
end
end
end
if isSameTable then
-- If all the tables are equal, then the intersection is that table (including NaNs).
-- All we need to do is convert it to an array and remove duplicate values.
for k, v in pairs(tableTemp) do
ret[#ret + 1] = v
exists[v] = true
end
return p.removeDuplicates(ret)
end
for val, count in pairs(vals) do
if count == lim then
ret[#ret + 1] = val
end
end
Line 267 ⟶ 80:
end
 
--[[
------------------------------------------------------------------------------------
-- complement
--
-- This returns the relative complement of t1, t2, ..., in tn. The complement
-- is of key/value pairs. This is equivalent to all the key/value pairs that are in
-- tn but are not in t1, t2, ... tn-1.
------------------------------------------------------------------------------------
--]]
function p.complement(...)
local lim = select('#', ...)
if lim == 0 then
error("no arguments passed to 'complement' (minimum is two)", 2)
elseif lim == 1 then
error("only one argument passed to 'complement' (minimum is two)", 2)
end
--[[
-- Now we know that we have at least two sets.
-- First, get all the key/value pairs in tn. We can't simply make ret equal to tn,
-- as that will affect the value of tn for the whole module.
--]]
local tn = select(lim, ...)
checkType('complement', lim, tn, 'table')
local ret = {}
for k, v in pairs(tn) do
ret[k] = v
end
-- Remove all the key/value pairs in t1, t2, ..., tn-1.
for i = 1, lim - 1 do
local t = select(i, ...)
checkType('complement', i, t, 'table')
for k, v in pairs(t) do
if ret[k] == v then
ret[k] = nil
end
end
end
return ret
end
 
--[[
------------------------------------------------------------------------------------
-- numKeys
Line 314 ⟶ 86:
-- keys that have non-nil values, sorted in numerical order.
------------------------------------------------------------------------------------
--]]
function p.numKeys(t)
checkType('numKeys', 1, t, 'table')
local isPositiveInteger = p.isPositiveInteger
local nums = {}
for k, v in pairs(t) do
if isPositiveInteger(k) then
nums[#nums + 1] = k
Line 328 ⟶ 99:
end
 
--[[
------------------------------------------------------------------------------------
-- affixNums
Line 334 ⟶ 104:
-- This takes a table and returns an array containing the numbers of keys with the
-- specified prefix and suffix. For example, for the table
-- {a1 = 'foo', a3 = 'bar', a6 = 'baz'} and the prefix "a", affixNums will return
-- return {1, 3, 6}.
------------------------------------------------------------------------------------
--]]
function p.affixNums(t, prefix, suffix)
checkType('affixNums', 1, t, 'table')
checkType('affixNums', 2, prefix, 'string', true)
checkType('affixNums', 3, suffix, 'string', true)
 
local function cleanPattern(s)
-- Cleans a pattern so that the magic characters ()%.[]*+-?^$ are interpreted literally.
return s:gsub('([%(%)%%%.%[%]%*%+%-%?%^%$])', '%%%1')
end
 
prefix = prefix or ''
suffix = suffix or ''
prefix = cleanPattern(prefix)
suffix = cleanPattern(suffix)
local pattern = '^' .. prefix .. '([1-9]%d*)' .. suffix .. '$'
 
local nums = {}
for k, v in pairs(t) do
if type(k) == 'string' then
local num = mw.ustring.match(k, pattern)
if num then
Line 358 ⟶ 136:
end
 
------------------------------------------------------------------------------------
--[[
-- numData
--
-- Given a table with keys like {"foo1", "bar1", "foo2", "baz2"}, returns a table
-- of subtables in the format
-- {[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". The
-- compress option compresses the table so that it can be iterated over with
-- ipairs.
------------------------------------------------------------------------------------
function p.numData(t, compress)
checkType('numData', 1, t, 'table')
checkType('numData', 2, compress, 'boolean', true)
local ret = {}
for k, v in pairs(t) do
local prefix, num = mw.ustring.match(tostring(k), '^([^0-9]*)([1-9][0-9]*)$')
if num then
num = tonumber(num)
local subtable = ret[num] or {}
if prefix == '' then
-- Positional parameters match the blank string; put them at the start of the subtable instead.
prefix = 1
end
subtable[prefix] = v
ret[num] = subtable
else
local subtable = ret.other or {}
subtable[k] = v
ret.other = subtable
end
end
if compress then
local other = ret.other
ret = p.compressSparseArray(ret)
ret.other = other
end
return ret
end
 
------------------------------------------------------------------------------------
-- compressSparseArray
Line 366 ⟶ 182:
-- ipairs.
------------------------------------------------------------------------------------
--]]
function p.compressSparseArray(t)
checkType('compressSparseArray', 1, t, 'table')
Line 377 ⟶ 192:
end
 
--[[
------------------------------------------------------------------------------------
-- sparseIpairs
Line 384 ⟶ 198:
-- handle nil values.
------------------------------------------------------------------------------------
--]]
function p.sparseIpairs(t)
checkType('sparseIpairs', 1, t, 'table')
Line 395 ⟶ 208:
local key = nums[i]
return key, t[key]
else
return nil, nil
end
end
end
 
--[[
------------------------------------------------------------------------------------
-- size
Line 406 ⟶ 220:
-- but for arrays it is more efficient to use the # operator.
------------------------------------------------------------------------------------
--]]
function p.size(t)
checkType('size', 1, t, 'table')
local i = 0
for k_ in pairs(t) do
i = i + 1
end
return i
end
 
local function defaultKeySort(item1, item2)
-- "number" < "string", so numbers will be sorted before strings.
local type1, type2 = type(item1), type(item2)
if type1 ~= type2 then
return type1 < type2
elseif type1 == 'table' or type1 == 'boolean' or type1 == 'function' then
return tostring(item1) < tostring(item2)
else
return item1 < item2
end
end
------------------------------------------------------------------------------------
-- keysToList
--
-- 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)
if not checked then
checkType('keysToList', 1, t, 'table')
checkTypeMulti('keysToList', 2, keySort, {'function', 'boolean', 'nil'})
end
 
local arr = {}
local index = 1
for k in pairs(t) do
arr[index] = k
index = index + 1
end
 
if keySort ~= false then
keySort = type(keySort) == 'function' and keySort or defaultKeySort
table.sort(arr, keySort)
end
 
return arr
end
 
------------------------------------------------------------------------------------
-- sortedPairs
--
-- 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)
checkType('sortedPairs', 1, t, 'table')
checkType('sortedPairs', 2, keySort, 'function', true)
 
local arr = p.keysToList(t, keySort, true)
 
local i = 0
return function ()
i = i + 1
local key = arr[i]
if key ~= nil then
return key, t[key]
else
return nil, nil
end
end
end
 
------------------------------------------------------------------------------------
-- isArray
--
-- Returns true if the given value is a table and all keys are consecutive
-- 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
for _ in pairs(v) do
i = i + 1
if v[i] == nil then
return false
end
end
return true
end
 
------------------------------------------------------------------------------------
-- invert
--
-- 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 = {}
for i, v in ipairs(arr) do
if not isNan(v) then
map[v] = i
end
end
 
return map
end
 
------------------------------------------------------------------------------------
-- listToSet
--
-- Creates a set from the array part of the table. Indexing the set by any of the
-- 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 = {}
for _, v in ipairs(arr) do
if not isNan(v) then
set[v] = true
end
end
 
return set
end
 
------------------------------------------------------------------------------------
-- deepCopy
--
-- Recursive deep copy function. Preserves identities of subtables.
------------------------------------------------------------------------------------
local function _deepCopy(orig, includeMetatable, already_seen)
if type(orig) ~= "table" then
return orig
end
-- already_seen stores copies of tables indexed by the original table.
local copy = already_seen[orig]
if copy ~= nil then
return copy
end
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)
end
if includeMetatable then
local mt = getmetatable(orig)
if mt ~= nil then
setmetatable(copy, _deepCopy(mt, true, already_seen))
end
end
return copy
end
 
function p.deepCopy(orig, noMetatable, already_seen)
checkType("deepCopy", 3, already_seen, "table", true)
return _deepCopy(orig, not noMetatable, already_seen or {})
end
 
------------------------------------------------------------------------------------
-- sparseConcat
--
-- 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)
local arr = {}
 
local arr_i = 0
for _, v in p.sparseIpairs(t) do
arr_i = arr_i + 1
arr[arr_i] = v
end
 
return table.concat(arr, sep, i, j)
end
 
------------------------------------------------------------------------------------
-- length
--
-- Finds the length of an array, or of a quasi-array with keys such as "data1",
-- "data2", etc., using an exponential search algorithm. It is similar to the
-- operator #, but may return a different value when there are gaps in the array
-- portion of the table. Intended to be used on data loaded with mw.loadData. For
-- other tables, use #.
-- 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)
-- requiring module inline so that [[Module:Exponential search]] which is
-- only needed by this one function doesn't get millions of transclusions
local expSearch = require("Module:Exponential search")
checkType('length', 1, t, 'table')
checkType('length', 2, prefix, 'string', true)
return expSearch(function (i)
local key
if prefix then
key = prefix .. tostring(i)
else
key = i
end
return t[key] ~= nil
end) or 0
end
 
------------------------------------------------------------------------------------
-- inArray
--
-- Returns true if valueToFind is a member of the array, and false otherwise.
------------------------------------------------------------------------------------
function p.inArray(arr, valueToFind)
checkType("inArray", 1, arr, "table")
-- if valueToFind is nil, error?
 
for _, v in ipairs(arr) do
if v == valueToFind then
return true
end
end
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
 
Retrieved from "https://en.wikipedia.org/wiki/Module:TableTools"