convert data formatting in a lua file - lua

hello i need to convert 720 data sets from a 1 liner to this format below.
Atm i got them in a open office file with each number in a column but i have no idea how i can convert that formatting.
12 -8906.071289 560.890564 93.236107 0 test2
13 -846.814636 -526.218323 10.981694 0 southshore
to
[12] = {
[1] = "test2",
[2] = "-8906.071289",
[3] = "560.890564",
[4] = "93.236107",
[5] = "0",
},
[13] = {
[1] = "Southshore",
[2] = "-846.814636",
[3] = "-526.218323",
[4] = "10.981694",
[5] = "0",
},

One possibility in Lua. Run with program.lua datafile
where program.lua is whatever name you give this file, and datafile is, well, your external data file. Test with just program.lua
--[[
12 -8906.071289 560.890564 93.236107 0 test2
13 -846.814636 -526.218323 10.981694 0 southshore
--]]
local filename = arg[1] or arg[0] --data from 1st command line argument or this file
local index,head,tail
print '{'
for line in io.lines(filename) do
if line:match '^%d+' then
head, line, tail = line:match '^(%d+)%s+(.-)(%S+)$'
print(' [' .. head .. '] = {\n [1] = "' .. tail .. '",')
index = 1
for line in line:gmatch '%S+' do
index = index + 1
print(' [' .. index .. '] = "' .. line .. '",')
end
print ' },'
end
end
print '}'

This awk program does it:
{
print "[" $1 "] = {"
print "\t[" 1 "] = \"" $NF "\","
for (i=2; i<NF; i++) {
print "\t[" i "] = \"" $i "\","
}
print "},"
}

Related

Parsing Lua strings, more specifically newlines

I'm trying to parse Lua 5.3 strings. However, I encountered an issue. For example,
$ lua
Lua 5.3.4 Copyright (C) 1994-2017 Lua.org, PUC-Rio
> print(load('return "\\z \n\r \n\r \r\n \n \n \\x"', "#test"))
nil test:6: hexadecimal digit expected near '"\x"'
>
> print(load('return "\\z\n\r\n\r\r\n\n\n\\x"', "#test"))
nil test:6: hexadecimal digit expected near '"\x"'
Both of these error on line 6, and the logic behind that is pretty simple: eat newline characters (\r or \n) if they're different from the current one (I believe this to be an accurate description of how the lua lexer works, but I may be wrong).
I have this code, which should do it:
local ln = 1
local skip = false
local mode = 0
local prev
for at, crlf in eaten:gmatch('()[\r\n]') do
local last = eaten:sub(at-1, at-1)
if skip and prev == last and last ~= crlf then
skip = false
else
skip = true
ln = ln + 1
end
prev = crlf
end
It decides whether to eat newlines based on the previous char. Now, from what I can tell, this should work, but no matter what I do it doesn't seem to work. Other attempts have made it report 5 lines, while this one makes it report 9(!). What am I missing here? I'm running this on Lua 5.2.4.
This is part of a routine for parsing \z:
local function parse52(s)
local startChar = string.sub(s,1,1)
if startChar~="'" and startChar~='"' then
error("not a string", 0)
end
local c = 0
local ln = 1
local t = {}
local nj = 1
local eos = #s
local pat = "^(.-)([\\" .. startChar .. "\r\n])"
local mkerr = function(emsg, ...)
error(string.format('[%s]:%d: ' .. emsg, s, ln, ...), 0)
end
local lnj
repeat
lnj = nj
local i, j, part, k = string.find(s, pat, nj + 1, false)
if i then
c = c + 1
t[c] = part
if simpleEscapes[v] then
--[[ some code, some elseifs, some more code ]]
elseif v == "z" then
local eaten, np = s:match("^([\t\n\v\f\r ]*)%f[^\t\n\v\f\r ]()", nj+1)
local p=np
nj = p-1
--[[ the newline counting routine above ]]
--[[ some other elseifs ]]
end
else
nj = nil
end
until not nj
if s:sub(-1, -1) ~= startChar then
mkerr("unfinished string near <eof>")
end
return table.concat(t)
end
Compact code for iterating lines of Lua script:
local text = "First\n\r\n\r\r\n\n\nSixth"
local ln = 1
for line, newline in text:gmatch"([^\r\n]*)([\r\n]*)" do
print(ln, line)
ln = ln + #newline:gsub("\n+", "\0%0\0"):gsub(".%z.", "."):gsub("%z", "")
end
Efficient code for iterating lines of Lua script:
local text = "First\n\r\n\r\r\n\n\nSixth"
local sub = string.sub
local ln = 1
for line, newline in text:gmatch'([^\r\n]*)([\r\n]*)' do
print(ln, line)
local pos, max_pos = 1, #newline
while pos <= max_pos do
local crlf = sub(newline, pos, pos + 1)
if crlf == "\r\n" or crlf == "\n\r" then
pos = pos + 2
else
pos = pos + 1
end
ln = ln + 1
end
end

Parsing a TeX-like language with lpeg

I am struggling to get my head around LPEG. I have managed to produce one grammar which does what I want, but I have been beating my head against this one and not getting far. The idea is to parse a document which is a simplified form of TeX. I want to split a document into:
Environments, which are \begin{cmd} and \end{cmd} pairs.
Commands which can either take an argument like so: \foo{bar} or can be bare: \foo.
Both environments and commands can have parameters like so: \command[color=green,background=blue]{content}.
Other stuff.
I also would like to keep track of line number information for error handling purposes. Here's what I have so far:
lpeg = require("lpeg")
lpeg.locale(lpeg)
-- Assume a lot of "X = lpeg.X" here.
-- Line number handling from http://lua-users.org/lists/lua-l/2011-05/msg00607.html
-- with additional print statements to check they are working.
local newline = P"\r"^-1 * "\n" / function (a) print("New"); end
local incrementline = Cg( Cb"linenum" )/ function ( a ) print("NL"); return a + 1 end , "linenum"
local setup = Cg ( Cc ( 1) , "linenum" )
nl = newline * incrementline
space = nl + lpeg.space
-- Taken from "Name-value lists" in http://www.inf.puc-rio.br/~roberto/lpeg/
local identifier = (R("AZ") + R("az") + P("_") + R("09"))^1
local sep = lpeg.S(",;") * space^0
local value = (1-lpeg.S(",;]"))^1
local pair = lpeg.Cg(C(identifier) * space ^0 * "=" * space ^0 * C(value)) * sep^-1
local list = lpeg.Cf(lpeg.Ct("") * pair^0, rawset)
local parameters = (P("[") * list * P("]")) ^-1
-- And the rest is mine
anything = C( (space^1 + (1-lpeg.S("\\{}")) )^1) * Cb("linenum") / function (a,b) return { text = a, line = b } end
begin_environment = P("\\begin") * Ct(parameters) * P("{") * Cg(identifier, "environment") * Cb("environment") * P("}") / function (a,b) return { params = a[1], environment = b } end
end_environment = P("\\end{") * Cg(identifier) * P("}")
texlike = lpeg.P{
"document";
document = setup * V("stuff") * -1,
stuff = Cg(V"environment" + anything + V"bracketed_stuff" + V"command_with" + V"command_without")^0,
bracketed_stuff = P"{" * V"stuff" * P"}" / function (a) return a end,
command_with =((P("\\") * Cg(identifier) * Ct(parameters) * Ct(V"bracketed_stuff"))-P("\\end{")) / function (i,p,n) return { command = i, parameters = p, nodes = n } end,
command_without = (( P("\\") * Cg(identifier) * Ct(parameters) )-P("\\end{")) / function (i,p) return { command = i, parameters = p } end,
environment = Cg(begin_environment * Ct(V("stuff")) * end_environment) / function (b,stuff, e) return { b = b, stuff = stuff, e = e} end
}
It almost works!
> texlike:match("\\foo[one=two]thing\\bar")
{
command = "foo",
parameters = {
{
one = "two",
},
},
}
{
line = 1,
text = "thing",
}
{
command = "bar",
parameters = {
},
}
But! First, I can't get the line number handling part to work at all. The function within incrementline is never fired.
I also can't quite work out how nested capture information is passed to handling functions (which is why I have scattered Cg, C and Ct semirandomly over the grammar). This means that only one item is returned from within a command_with:
> texlike:match("\\foo{text \\command moretext}")
{
command = "foo",
nodes = {
{
line = 1,
text = "text ",
},
},
parameters = {
},
}
I would also love to be able to check that the environment start and ends match up but when I tried to do so, my back references from "begin" were not in scope by the time I got to "end". I don't know where to go from here.
Late answer but hopefully it'll offer some insight if you're still looking for a solution or wondering what the problem was.
There are a couple of issues with your grammar, some of which can be tricky to spot.
Your line increment here looks incorrect:
local incrementline = Cg( Cb"linenum" ) /
function ( a ) print("NL"); return a + 1 end,
"linenum"
It looks like you meant to create a named capture group and not an anonymous group. The backcapture linenum is essentially being used like a variable. The problem is because this is inside an anonymous capture, linenum will not update properly -- function(a) will always receive 1 when called. You need to move the closing ) to the end so "linenum" is included:
local incrementline = Cg( Cb"linenum" /
function ( a ) print("NL"); return a + 1 end,
"linenum")
Relevant LPeg documentation for Cg capture.
The second problem is with your anything non-terminal rule:
anything = C( (space^1 + (1-lpeg.S("\\{}")) )^1) * Cb("linenum") ...
There are several things to be careful here. First, a named Cg capture (from incrementline rule once it's fixed) doesn't produce anything unless it's in a table or you backref it. The second major thing is that it has an adhoc scope like a variable. More precisely, its scope ends once you close it in an outer capture -- like what you're doing here:
C( (space^1 + (...) )^1)
Which means by the time you reference its backcapture with * Cb("linenum"), that's already too late -- the linenum you really want already closed its scope.
I always found LPeg's re syntax a bit easier to grok so I've rewritten the grammar with that instead:
local grammar_cb =
{
fold = pairfold,
resetlinenum = resetlinenum,
incrementlinenum = incrementlinenum, getlinenum = getlinenum,
error = error
}
local texlike_grammar = re.compile(
[[
document <- '' -> resetlinenum {| docpiece* |} !.
docpiece <- {| envcmd |} / {| cmd |} / multiline
beginslash <- cmdslash 'begin'
endslash <- cmdslash 'end'
envcmd <- beginslash paramblock? {:beginenv: envblock :} (!endslash docpiece)*
endslash openbrace {:endenv: =beginenv :} closebrace / &beginslash {} -> error .
envblock <- openbrace key closebrace
cmd <- cmdslash {:command: identifier :} (paramblock? cmdblock)?
cmdblock <- openbrace {:nodes: {| docpiece* |} :} closebrace
paramblock <- opensq ( {:parameters: {| parampairs |} -> fold :} / whitesp) closesq
parampairs <- parampair (sep parampair)*
parampair <- key assign value
key <- whitesp { identifier }
value <- whitesp { [^],;%s]+ }
multiline <- (nl? text)+
text <- {| {:text: (!cmd !closebrace !%nl [_%w%p%s])+ :} {:line: '' -> getlinenum :} |}
identifier <- [_%w]+
cmdslash <- whitesp '\'
assign <- whitesp '='
sep <- whitesp ','
openbrace <- whitesp '{'
closebrace <- whitesp '}'
opensq <- whitesp '['
closesq <- whitesp ']'
nl <- {%nl+} -> incrementlinenum
whitesp <- (nl / %s)*
]], grammar_cb)
The callback functions are straight-forwardly defined as:
local function pairfold(...)
local t, kv = {}, ...
if #kv % 2 == 1 then return ... end
for i = #kv, 2, -2 do
t[ kv[i - 1] ] = kv[i]
end
return t
end
local incrementlinenum, getlinenum, resetlinenum do
local line = 1
function incrementlinenum(nl)
assert(not nl:match "%S")
line = line + #nl
end
function getlinenum() return line end
function resetlinenum() line = 1 end
end
Testing the grammar with a non-trivial tex-like str with multiple lines:
local test1 = [[\foo{text \bar[color = red, background = black]{
moretext \baz{
even
more text} }
this time skipping multiple
lines even, such wow!}]]
Produces the follow AST in lua-table format:
{
command = "foo",
nodes = {
{
text = "text",
line = 1
},
{
parameters = {
color = "red",
background = "black"
},
command = "bar",
nodes = {
{
text = " moretext",
line = 2
},
{
command = "baz",
nodes = {
{
text = "even ",
line = 3
},
{
text = "more text",
line = 4
}
}
}
}
},
{
text = "this time skipping multiple",
line = 7
},
{
text = "lines even, such wow!",
line = 9
}
}
}
And a second test for begin/end environments:
local test2 = [[\begin[p1
=apple,
p2=blue]{scope} scope foobar
\end{scope} global foobar]]
Which seems to give approximately what you're looking for:
{
{
{
text = " scope foobar",
line = 3
},
parameters = {
p1 = "apple",
p2 = "blue"
},
beginenv = "scope",
endenv = "scope"
},
{
text = " global foobar",
line = 4
}
}

lua loops stuck after 15 numbers

My code is designed to read digits and turn them into Chinese pinyin:
function digitconverter (digit)
if digit == "0" then
cnumber = "ying2 "
elseif digit == "1" then
cnumber = "yi1 "
elseif digit == "2" then
cnumber = "er2 "
elseif digit == "3" then
cnumber = "san1 "
elseif digit == "4" then
cnumber = "si4 "
elseif digit == "5" then
cnumber = "wu3 "
elseif digit == "6" then
cnumber = "liu4 "
elseif digit == "7" then
cnumber = "qi1 "
elseif digit == "8" then
cnumber = "ba1 "
elseif digit == "9" then
cnumber = "jiu3 "
end
return cnumber
end
print("Enter a number to be converted:")
repeat
strnumber = io.read("*line")
number = tonumber(strnumber)
if number ~= nil then
continue = true
else
print("Invalid input. Please try again:")
continue = false
end
until continue == true
nlength = #strnumber
digits = {}
for d in string.gmatch(number, "%d") do
digits[#digits + 1] = d
end
convnumber = ""
for d=1,nlength do
convnumber = convnumber .. digitconverter(digits[d])
end
print(convnumber)
io.read()
If I enter over 15 digits, it gets stuck (for lack of a better term). It WILL convert every digit, but the 16th will be random and the 17th and on will repeat another random one. I've been over it and I can't figure out where it's getting hung up. Thoughts?
You're iterating through the digits of number, not strnumber. The problem is when you get to too many digits, the string representation is going to be in scientific notation:
strnumber = '1234567890123456789'
number = tonumber(strnumber)
print(number) --> 1.2345678901235e+018
Side note: Lua is based on hashtables, which gives you (barring hash collisions) constant time lookup. So your digit converter can be simply written as a map:
local digitmap = {
["0"] = "ying2 ",
["1"] = "yi1 ",
["2"] = "er2 ",
["3"] = "san1 ",
["4"] = "si4 ",
["5"] = "wu3 ",
["6"] = "liu4 ",
["7"] = "qi1 ",
["8"] = "ba1 ",
["9"] = "jiu3 ",
}
Also, building strings like this is very inefficient:
for d=1,nlength do
convnumber = convnumber .. digitconverter(digits[d])
end
You're generating tons of intermediate strings, which requires a lot of allocations and produces a lot of garbage. It's much faster to put all the values you need to concatenate into a table, then call table.concat. Another advantage is that you can specify a delimiter (right now, you're hard coding the delimiter into your string table).
Using those techniques, we can rewrite your code like this:
local digitmap = {
['0'] = 'ying2',
['1'] = 'yi1',
['2'] = 'er2',
['3'] = 'san1',
['4'] = 'si4',
['5'] = 'wu3',
['6'] = 'liu4',
['7'] = 'qi1',
['8'] = 'ba1',
['9'] = 'jiu3',
}
print('Enter a number to be converted:')
while true do
strnumber = io.read('*line')
if not strnumber:match('%D') then
break
end
print('Invalid input. Please try again:')
end
local digits = {}
for digit in string.gmatch(strnumber, '%d') do
digits[#digits + 1] = digitmap[digit]
end
print(table.concat(digits, ' '))
Probably, you want to scan strnumber instead of number in the following line of your code:
for d in string.gmatch(number, "%d") do
Your number variable contains a numerical value in double format with 15-16 decimal digits.

How do you reference a table with a key value that is numeric in Lua?

The output for the below script is:
AD[1] = [variable not found]
AD['2'] = bar
How can I modify the function getfield to return a value for v for both cases?
function getfield (f)
local v = _G
for w in string.gfind(f, "[%w_]+") do
v = v[w]
end
return v
end
AD = {[1] = 'foo', ['2'] = 'bar'}
data = {"AD[1]","AD['2']"}
for i,line in ipairs(data) do
s = getfield(line)
if s then
print(line .. " = " .. s)
else
print(line .. " = [variable not found]")
end
end
UPDATE:
I'm 90% sure, this is going to work for me:
function getfield (f)
local v = _G
for w in string.gfind(f, "['%w_]+") do
if (string.find(w,"['%a_]")==nil) then
w = loadstring('return '..w)()
else
w = string.gsub(w, "'", "")
end
v=v[w]
end
return v
end
This happens to work
function getfield (f)
local v = _G
for w in string.gfind(f, "['%w_]+") do
local x = loadstring('return '..w)()
print(w,x)
v = v[x] or v[w]
end
return v
end
AD = {[1] = 'foo', ['2'] = 'bar'}
data = {"AD[1]","AD['2']"}
for i,line in ipairs(data) do
s = getfield(line)
if s then
print(line .. " = " .. s)
else
print(line .. " = [variable not found]")
end
end
but it's pretty fragile.
Note that I added ' to the pattern.
The difficulty is that sometimes w is a string representing a name (key), and sometimes it's a string representing a number. In the second case it needs to be converted from string to number. But you need the context or some syntax to decide.
Here's the kind of fragility I mean:
> data = {"math[pi]","AD['2']"}
>
> for i,line in ipairs(data) do
>> s = getfield(line)
>> if s then
>> print(line .. " = " .. s)
>> else
>> print(line .. " = [variable not found]")
>> end
>> end
math table: 0x10ee05100
pi nil
math[pi] = 3.1415926535898
AD table: 0x10ee19ee0
'2' 2
AD['2'] = bar
> pi = 3
> math[3] = 42
> data = {"math[pi]","AD['2']"}>
> for i,line in ipairs(data) do
>> s = getfield(line)
>> if s then
>> print(line .. " = " .. s)
>> else
>> print(line .. " = [variable not found]")
>> end
>> end
math table: 0x10ee05100
pi 3
math[pi] = 42
AD table: 0x10ee19ee0
'2' 2
AD['2'] = bar
math[pi] is unchanged, but getfield interprets pi in the global context and gets 3 so the wrong field of math is returned.
You'll get the strings '1' and "'2'". You have to evaluate it to turn it into whatever object it is:
v = v[loadstring('return ' .. w)()]
Don't do this if the string came from an untrusted source though (like a user input or something) because they could execute arbitrary code.

How to dump a table to console?

I'm having trouble displaying the contents of a table which contains nested tables (n-deep). I'd like to just dump it to std out or the console via a print statement or something quick and dirty but I can't figure out how. I'm looking for the rough equivalent that I'd get when printing an NSDictionary using gdb.
If the requirement is "quick and dirty"
I've found this one useful. Because of the recursion it can print nested tables too. It doesn't give the prettiest formatting in the output but for such a simple function it's hard to beat for debugging.
function dump(o)
if type(o) == 'table' then
local s = '{ '
for k,v in pairs(o) do
if type(k) ~= 'number' then k = '"'..k..'"' end
s = s .. '['..k..'] = ' .. dump(v) .. ','
end
return s .. '} '
else
return tostring(o)
end
end
e.g.
local people = {
{
name = "Fred",
address = "16 Long Street",
phone = "123456"
},
{
name = "Wilma",
address = "16 Long Street",
phone = "123456"
},
{
name = "Barney",
address = "17 Long Street",
phone = "123457"
}
}
print("People:", dump(people))
Produces the following output:
People: { [1] = { ["address"] = 16 Long Street,["phone"] =
123456,["name"] = Fred,} ,[2] = { ["address"] = 16 Long
Street,["phone"] = 123456,["name"] = Wilma,} ,[3] = { ["address"] = 17
Long Street,["phone"] = 123457,["name"] = Barney,} ,}
I know this question has already been marked as answered, but let me plug my own library here. It's called inspect.lua, and you can find it here:
https://github.com/kikito/inspect.lua
It's just a single file that you can require from any other file. It returns a function that transforms any Lua value into a human-readable string:
local inspect = require('inspect')
print(inspect({1,2,3})) -- {1, 2, 3}
print(inspect({a=1,b=2})
-- {
-- a = 1
-- b = 2
-- }
It indents subtables properly, and handles "recursive tables" (tables that contain references to themselves) correctly, so it doesn't get into infinite loops. It sorts values in a sensible way. It also prints metatable information.
Regards!
Feel free to browse the Lua Wiki on table serialization. It lists several ways on how to dump a table to the console.
You just have to choose which one suits you best. There are many ways to do it, but I usually end up using the one from Penlight:
> t = { a = { b = { c = "Hello world!", 1 }, 2, d = { 3 } } }
> require 'pl.pretty'.dump(t)
{
a = {
d = {
3
},
b = {
c = "Hello world!",
1
},
2
}
}
found this:
-- Print contents of `tbl`, with indentation.
-- `indent` sets the initial level of indentation.
function tprint (tbl, indent)
if not indent then indent = 0 end
for k, v in pairs(tbl) do
formatting = string.rep(" ", indent) .. k .. ": "
if type(v) == "table" then
print(formatting)
tprint(v, indent+1)
elseif type(v) == 'boolean' then
print(formatting .. tostring(v))
else
print(formatting .. v)
end
end
end
from here
https://gist.github.com/ripter/4270799
works pretty good for me...
Most pure lua print table functions I've seen have a problem with deep recursion
and tend to cause a stack overflow when going too deep. This print
table function that I've written does not have this problem. It should also be capable of handling really large tables due to the way it handles concatenation. In my personal usage of this function, it outputted 63k lines to file in about a second.
The output also keeps lua syntax and the script can easily be modified
for simple persistent storage by writing the output to file if modified to allow
only number, boolean, string and table data types to be formatted.
function print_table(node)
local cache, stack, output = {},{},{}
local depth = 1
local output_str = "{\n"
while true do
local size = 0
for k,v in pairs(node) do
size = size + 1
end
local cur_index = 1
for k,v in pairs(node) do
if (cache[node] == nil) or (cur_index >= cache[node]) then
if (string.find(output_str,"}",output_str:len())) then
output_str = output_str .. ",\n"
elseif not (string.find(output_str,"\n",output_str:len())) then
output_str = output_str .. "\n"
end
-- This is necessary for working with HUGE tables otherwise we run out of memory using concat on huge strings
table.insert(output,output_str)
output_str = ""
local key
if (type(k) == "number" or type(k) == "boolean") then
key = "["..tostring(k).."]"
else
key = "['"..tostring(k).."']"
end
if (type(v) == "number" or type(v) == "boolean") then
output_str = output_str .. string.rep('\t',depth) .. key .. " = "..tostring(v)
elseif (type(v) == "table") then
output_str = output_str .. string.rep('\t',depth) .. key .. " = {\n"
table.insert(stack,node)
table.insert(stack,v)
cache[node] = cur_index+1
break
else
output_str = output_str .. string.rep('\t',depth) .. key .. " = '"..tostring(v).."'"
end
if (cur_index == size) then
output_str = output_str .. "\n" .. string.rep('\t',depth-1) .. "}"
else
output_str = output_str .. ","
end
else
-- close the table
if (cur_index == size) then
output_str = output_str .. "\n" .. string.rep('\t',depth-1) .. "}"
end
end
cur_index = cur_index + 1
end
if (size == 0) then
output_str = output_str .. "\n" .. string.rep('\t',depth-1) .. "}"
end
if (#stack > 0) then
node = stack[#stack]
stack[#stack] = nil
depth = cache[node] == nil and depth + 1 or depth - 1
else
break
end
end
-- This is necessary for working with HUGE tables otherwise we run out of memory using concat on huge strings
table.insert(output,output_str)
output_str = table.concat(output)
print(output_str)
end
Here is an example:
local t = {
["abe"] = {1,2,3,4,5},
"string1",
50,
["depth1"] = { ["depth2"] = { ["depth3"] = { ["depth4"] = { ["depth5"] = { ["depth6"] = { ["depth7"]= { ["depth8"] = { ["depth9"] = { ["depth10"] = {1000}, 900}, 800},700},600},500}, 400 }, 300}, 200}, 100},
["ted"] = {true,false,"some text"},
"string2",
[function() return end] = function() return end,
75
}
print_table(t)
Output:
{
[1] = 'string1',
[2] = 50,
[3] = 'string2',
[4] = 75,
['abe'] = {
[1] = 1,
[2] = 2,
[3] = 3,
[4] = 4,
[5] = 5
},
['function: 06472B70'] = 'function: 06472A98',
['depth1'] = {
[1] = 100,
['depth2'] = {
[1] = 200,
['depth3'] = {
[1] = 300,
['depth4'] = {
[1] = 400,
['depth5'] = {
[1] = 500,
['depth6'] = {
[1] = 600,
['depth7'] = {
[1] = 700,
['depth8'] = {
[1] = 800,
['depth9'] = {
[1] = 900,
['depth10'] = {
[1] = 1000
}
}
}
}
}
}
}
}
}
},
['ted'] = {
[1] = true,
[2] = false,
[3] = 'some text'
}
}
As previously mentioned, you have to write it.
Here is my humble version: (super basic one)
function tprint (t, s)
for k, v in pairs(t) do
local kfmt = '["' .. tostring(k) ..'"]'
if type(k) ~= 'string' then
kfmt = '[' .. k .. ']'
end
local vfmt = '"'.. tostring(v) ..'"'
if type(v) == 'table' then
tprint(v, (s or '')..kfmt)
else
if type(v) ~= 'string' then
vfmt = tostring(v)
end
print(type(t)..(s or '')..kfmt..' = '..vfmt)
end
end
end
example:
local mytbl = { ['1']="a", 2, 3, b="c", t={d=1} }
tprint(mytbl)
output (Lua 5.0):
table[1] = 2
table[2] = 3
table["1"] = "a"
table["t"]["d"] = 1
table["b"] = "c"
I use my own function to print the contents of a table but not sure how well it translates to your environment:
---A helper function to print a table's contents.
---#param tbl table #The table to print.
---#param depth number #The depth of sub-tables to traverse through and print.
---#param n number #Do NOT manually set this. This controls formatting through recursion.
function PrintTable(tbl, depth, n)
n = n or 0;
depth = depth or 5;
if (depth == 0) then
print(string.rep(' ', n).."...");
return;
end
if (n == 0) then
print(" ");
end
for key, value in pairs(tbl) do
if (key and type(key) == "number" or type(key) == "string") then
key = string.format("[\"%s\"]", key);
if (type(value) == "table") then
if (next(value)) then
print(string.rep(' ', n)..key.." = {");
PrintTable(value, depth - 1, n + 4);
print(string.rep(' ', n).."},");
else
print(string.rep(' ', n)..key.." = {},");
end
else
if (type(value) == "string") then
value = string.format("\"%s\"", value);
else
value = tostring(value);
end
print(string.rep(' ', n)..key.." = "..value..",");
end
end
end
if (n == 0) then
print(" ");
end
end
The simplest way, with circular reference handling and all:
function dump(t, indent, done)
done = done or {}
indent = indent or 0
done[t] = true
for key, value in pairs(t) do
print(string.rep("\t", indent))
if type(value) == "table" and not done[value] then
done[value] = true
print(key, ":\n")
dump(value, indent + 2, done)
done[value] = nil
else
print(key, "\t=\t", value, "\n")
end
end
end
There are 2 solutions that I want to mention: a quick&dirty one, and another which properly escapes all keys and values but is bigger
Simple & fast solution (use only on "safe" inputs):
local function format_any_value(obj, buffer)
local _type = type(obj)
if _type == "table" then
buffer[#buffer + 1] = '{"'
for key, value in next, obj, nil do
buffer[#buffer + 1] = tostring(key) .. '":'
format_any_value(value, buffer)
buffer[#buffer + 1] = ',"'
end
buffer[#buffer] = '}' -- note the overwrite
elseif _type == "string" then
buffer[#buffer + 1] = '"' .. obj .. '"'
elseif _type == "boolean" or _type == "number" then
buffer[#buffer + 1] = tostring(obj)
else
buffer[#buffer + 1] = '"???' .. _type .. '???"'
end
end
Usage:
local function format_as_json(obj)
if obj == nil then return "null" else
local buffer = {}
format_any_value(obj, buffer)
return table.concat(buffer)
end
end
local function print_as_json(obj)
print(_format_as_json(obj))
end
print_as_json {1, 2, 3}
print_as_json(nil)
print_as_json("string")
print_as_json {[1] = 1, [2] = 2, three = { { true } }, four = "four"}
Correct solution with key/value escaping
Small library that I wrote in pure Lua for this specific use-case: https://github.com/vn971/fast_json_encode
Or specifically this 1 file that includes both a formatter and a printer: https://github.com/vn971/fast_json_encode/blob/master/json_format.lua
You have to code it yourself I'm afraid. I wrote this, and it may be of some use to you
function printtable(table, indent)
indent = indent or 0;
local keys = {};
for k in pairs(table) do
keys[#keys+1] = k;
table.sort(keys, function(a, b)
local ta, tb = type(a), type(b);
if (ta ~= tb) then
return ta < tb;
else
return a < b;
end
end);
end
print(string.rep(' ', indent)..'{');
indent = indent + 1;
for k, v in pairs(table) do
local key = k;
if (type(key) == 'string') then
if not (string.match(key, '^[A-Za-z_][0-9A-Za-z_]*$')) then
key = "['"..key.."']";
end
elseif (type(key) == 'number') then
key = "["..key.."]";
end
if (type(v) == 'table') then
if (next(v)) then
printf("%s%s =", string.rep(' ', indent), tostring(key));
printtable(v, indent);
else
printf("%s%s = {},", string.rep(' ', indent), tostring(key));
end
elseif (type(v) == 'string') then
printf("%s%s = %s,", string.rep(' ', indent), tostring(key), "'"..v.."'");
else
printf("%s%s = %s,", string.rep(' ', indent), tostring(key), tostring(v));
end
end
indent = indent - 1;
print(string.rep(' ', indent)..'}');
end
The table.tostring metehod of metalua is actually very complete. It deals with nested tables, the indentation level is changeable, ...
See https://github.com/fab13n/metalua/blob/master/src/lib/metalua/table2.lua
This is my version that supports excluding tables and userdata
-- Lua Table View by Elertan
table.print = function(t, exclusions)
local nests = 0
if not exclusions then exclusions = {} end
local recurse = function(t, recurse, exclusions)
indent = function()
for i = 1, nests do
io.write(" ")
end
end
local excluded = function(key)
for k,v in pairs(exclusions) do
if v == key then
return true
end
end
return false
end
local isFirst = true
for k,v in pairs(t) do
if isFirst then
indent()
print("|")
isFirst = false
end
if type(v) == "table" and not excluded(k) then
indent()
print("|-> "..k..": "..type(v))
nests = nests + 1
recurse(v, recurse, exclusions)
elseif excluded(k) then
indent()
print("|-> "..k..": "..type(v))
elseif type(v) == "userdata" or type(v) == "function" then
indent()
print("|-> "..k..": "..type(v))
elseif type(v) == "string" then
indent()
print("|-> "..k..": ".."\""..v.."\"")
else
indent()
print("|-> "..k..": "..v)
end
end
nests = nests - 1
end
nests = 0
print("### START TABLE ###")
for k,v in pairs(t) do
print("root")
if type(v) == "table" then
print("|-> "..k..": "..type(v))
nests = nests + 1
recurse(v, recurse, exclusions)
elseif type(v) == "userdata" or type(v) == "function" then
print("|-> "..k..": "..type(v))
elseif type(v) == "string" then
print("|-> "..k..": ".."\""..v.."\"")
else
print("|-> "..k..": "..v)
end
end
print("### END TABLE ###")
end
This is an example
t = {
location = {
x = 10,
y = 20
},
size = {
width = 100000000,
height = 1000,
},
name = "Sidney",
test = {
hi = "lol",
},
anotherone = {
1,
2,
3
}
}
table.print(t, { "test" })
Prints:
### START TABLE ###
root
|-> size: table
|
|-> height: 1000
|-> width: 100000000
root
|-> location: table
|
|-> y: 20
|-> x: 10
root
|-> anotherone: table
|
|-> 1: 1
|-> 2: 2
|-> 3: 3
root
|-> test: table
|
|-> hi: "lol"
root
|-> name: "Sidney"
### END TABLE ###
Notice that the root doesn't remove exclusions
Made this version to print tables with identation. Can probably be extended to work recursively.
function printtable(table, indent)
print(tostring(table) .. '\n')
for index, value in pairs(table) do
print(' ' .. tostring(index) .. ' : ' .. tostring(value) .. '\n')
end
end
--~ print a table
function printTable(list, i)
local listString = ''
--~ begin of the list so write the {
if not i then
listString = listString .. '{'
end
i = i or 1
local element = list[i]
--~ it may be the end of the list
if not element then
return listString .. '}'
end
--~ if the element is a list too call it recursively
if(type(element) == 'table') then
listString = listString .. printTable(element)
else
listString = listString .. element
end
return listString .. ', ' .. printTable(list, i + 1)
end
local table = {1, 2, 3, 4, 5, {'a', 'b'}, {'G', 'F'}}
print(printTable(table))
Hi man, I wrote a siple code that do this in pure Lua, it has a bug (write a coma after the last element of the list) but how i wrote it quickly as a prototype I will let it to you adapt it to your needs.
Adding another version. This one tries to iterate over userdata as well.
function inspect(o,indent)
if indent == nil then indent = 0 end
local indent_str = string.rep(" ", indent)
local output_it = function(str)
print(indent_str..str)
end
local length = 0
local fu = function(k, v)
length = length + 1
if type(v) == "userdata" or type(v) == 'table' then
output_it(indent_str.."["..k.."]")
inspect(v, indent+1)
else
output_it(indent_str.."["..k.."] "..tostring(v))
end
end
local loop_pairs = function()
for k,v in pairs(o) do fu(k,v) end
end
local loop_metatable_pairs = function()
for k,v in pairs(getmetatable(o)) do fu(k,v) end
end
if not pcall(loop_pairs) and not pcall(loop_metatable_pairs) then
output_it(indent_str.."[[??]]")
else
if length == 0 then
output_it(indent_str.."{}")
end
end
end
Convert to json and then print.
local json = require('cjson')
json_string = json.encode(this_table)
print (json_string)
simple example of dump a table in lua
i suggest using serpent.lua
local function parser(value, indent, subcategory)
local indent = indent or 2
local response = '(\n'
local subcategory = type(subcategory) == 'number' and subcategory or indent
for key, value in pairs(value) do
if type(value) == 'table' then
value = parser(value, indent, subcategory + indent)
elseif type(value) == 'string' then
value = '\''.. value .. '\''
elseif type(value) ~= 'number' then
value = tostring(value)
end
if type(tonumber(key)) == 'number' then
key = '[' .. key .. ']'
elseif not key:match('^([A-Za-z_][A-Za-z0-9_]*)$') then
key = '[\'' .. key .. '\']'
end
response = response .. string.rep(' ', subcategory) .. key .. ' = ' .. value .. ',\n'
end
return response .. string.rep(' ', subcategory - indent) .. ')'
end
example
response = parser{1,2,3, {ok = 10, {}}}
print(response)
result
(
[1] = 1,
[2] = 2,
[3] = 3,
[4] = (
[1] = (),
ok = 10
)
)
here's my little snippet for that:
--- Dump value of a variable in a formatted string
--
--- #param o table Dumpable object
--- #param tbs string|nil Tabulation string, ' ' by default
--- #param tb number|nil Initial tabulation level, 0 by default
--- #return string
local function dump(o, tbs, tb)
tb = tb or 0
tbs = tbs or ' '
if type(o) == 'table' then
local s = '{'
if (next(o)) then s = s .. '\n' else return s .. '}' end
tb = tb + 1
for k,v in pairs(o) do
if type(k) ~= 'number' then k = '"' .. k .. '"' end
s = s .. tbs:rep(tb) .. '[' .. k .. '] = ' .. dump(v, tbs, tb)
s = s .. ',\n'
end
tb = tb - 1
return s .. tbs:rep(tb) .. '}'
else
return tostring(o)
end
end
I have humbly modified a bit Alundaio code:
-- by Alundaio
-- KK modified 11/28/2019
function dump_table_to_string(node, tree, indentation)
local cache, stack, output = {},{},{}
local depth = 1
if type(node) ~= "table" then
return "only table type is supported, got " .. type(node)
end
if nil == indentation then indentation = 1 end
local NEW_LINE = "\n"
local TAB_CHAR = " "
if nil == tree then
NEW_LINE = "\n"
elseif not tree then
NEW_LINE = ""
TAB_CHAR = ""
end
local output_str = "{" .. NEW_LINE
while true do
local size = 0
for k,v in pairs(node) do
size = size + 1
end
local cur_index = 1
for k,v in pairs(node) do
if (cache[node] == nil) or (cur_index >= cache[node]) then
if (string.find(output_str,"}",output_str:len())) then
output_str = output_str .. "," .. NEW_LINE
elseif not (string.find(output_str,NEW_LINE,output_str:len())) then
output_str = output_str .. NEW_LINE
end
-- This is necessary for working with HUGE tables otherwise we run out of memory using concat on huge strings
table.insert(output,output_str)
output_str = ""
local key
if (type(k) == "number" or type(k) == "boolean") then
key = "["..tostring(k).."]"
else
key = "['"..tostring(k).."']"
end
if (type(v) == "number" or type(v) == "boolean") then
output_str = output_str .. string.rep(TAB_CHAR,depth*indentation) .. key .. " = "..tostring(v)
elseif (type(v) == "table") then
output_str = output_str .. string.rep(TAB_CHAR,depth*indentation) .. key .. " = {" .. NEW_LINE
table.insert(stack,node)
table.insert(stack,v)
cache[node] = cur_index+1
break
else
output_str = output_str .. string.rep(TAB_CHAR,depth*indentation) .. key .. " = '"..tostring(v).."'"
end
if (cur_index == size) then
output_str = output_str .. NEW_LINE .. string.rep(TAB_CHAR,(depth-1)*indentation) .. "}"
else
output_str = output_str .. ","
end
else
-- close the table
if (cur_index == size) then
output_str = output_str .. NEW_LINE .. string.rep(TAB_CHAR,(depth-1)*indentation) .. "}"
end
end
cur_index = cur_index + 1
end
if (size == 0) then
output_str = output_str .. NEW_LINE .. string.rep(TAB_CHAR,(depth-1)*indentation) .. "}"
end
if (#stack > 0) then
node = stack[#stack]
stack[#stack] = nil
depth = cache[node] == nil and depth + 1 or depth - 1
else
break
end
end
-- This is necessary for working with HUGE tables otherwise we run out of memory using concat on huge strings
table.insert(output,output_str)
output_str = table.concat(output)
return output_str
end
then:
print(dump_table_to_string("AA", true,3))
print(dump_table_to_string({"AA","BB"}, true,3))
print(dump_table_to_string({"AA","BB"}))
print(dump_table_to_string({"AA","BB"},false))
print(dump_table_to_string({"AA","BB",{22,33}},true,2))
gives:
only table type is supported, got string
{
[1] = 'AA',
[2] = 'BB'
}
{
[1] = 'AA',
[2] = 'BB'
}
{[1] = 'AA',[2] = 'BB'}
{
[1] = 'AA',
[2] = 'BB',
[3] = {
[1] = 22,
[2] = 33
}
}
Now the function print can print the (flat) tables!
oprint = print -- origin print
print = function (...)
if type(...) == "table" then
local str = ''
local amount = 0
for i,v in pairs(...) do
amount=amount+1
local pre = type(i) == "string" and i.."=" or ""
str = str .. pre..tostring(v) .. "\t"
end
oprint('#'..amount..':', str)
else
oprint(...)
end
end
For example:
print ({x=7, y=9, w=11, h="height", 7, 8, 9})
prints:
#7: 7 8 9 y=9 x=7 h=height w=11
The same way it can be just new function tostring:
otostring = tostring -- origin tostring
tostring = function (...)
if type(...) == "table" then
local str = '{'
for i,v in pairs(...) do
local pre = type(i) == "string" and i.."=" or ""
str = str .. pre..tostring(v) .. ", "
end
str = str:sub(1, -3)
return str..'}'
else
return otostring(...)
end
end

Resources