'Convert Lua data to JSON
This EPGP World of Warcraft addon outputs an epgp.lua database file.
I wrote a plugin to convert the Lua data into a JSON object for display on a guild website. It was working in older versions of the addon, but now I'm having trouble trying to get it to convert the file properly. Here are two snippets that show the conversion problem - see this demo.
The first works great at forming a nested array:
["roster_info"] = {
{
"Agantica", -- [1]
"ROGUE", -- [2]
"09/03-2013", -- [3]
}, -- [1]
{
"Intikamim", -- [1]
"PALADIN", -- [2]
"17/02-2013", -- [3]
}, -- [2]
},
becomes
"roster_info" : [
[
"Agantica",
"ROGUE",
"09/03-2013"
],
[
"Intikamim",
"PALADIN",
"17/02-2013"
]
]
But the string replacment sees this next snippet as a nested array when it should be an object inside of an array:
["bonus_loot_log"] = {
{
["player"] = "Magebox",
["timestamp"] = "2013-03-07 13:44:00",
["coinsLeft"] = "-1",
["reward"] = "|cffa335ee|Hitem:86815:0:0:0:0:0:0:632235520:90:0:445|h[Attenuating Bracers]|h|r",
}, -- [1]
{
["player"] = "Lîutasila",
["coinsLeft"] = "-1",
["timestamp"] = "2013-03-07 13:47:00",
}, -- [2]
},
becomes
"bonus_loot_log" : [
[
"player" : "Magebox",
"timestamp" : "2013-03-07 13:44:00",
"coinsLeft" : "-1",
"reward" : "|cffa335ee|Hitem:86815:0:0:0:0:0:0:632235520:90:0:445|h[Attenuating Bracers]|h|r"
],
[
"player": "Lîutasila",
"coinsLeft": "-1",
"timestamp": "2013-03-07 13:47:00"
]
]
Here is the string conversion script that only works on the first snippet.
lua_string
.replace(/\[(.*)\]\s\=\s/g,'$1:') // change equal to colon & remove outer brackets
.replace(/[\t\r\n]/g,'') // remove tabs & returns
.replace(/\}\,\s--\s\[\d+\]\}/g,']]') // replace sets ending with a comment with square brackets
.replace(/\,\s--\s\[\d+\]/g,',') // remove close subgroup and comment
.replace(/,(\}|\])/g,'$1') // remove trailing comma
.replace(/\}\,\{/g,'],[') // replace curly bracket set with square brackets
.replace(/\{\{/g,'[[') // change double curlies to square brackets
.replace(/EPGP_DB\s\=/,'');
So, I need some help getting the Lua to convert properly with an array of objects (second example).
Solution 1:[1]
You generally cannot convert any Lua table to JSON data simply by using string operations. The problem is that while Lua uses tables for both arrays and dictionaries, JSON needs two different types. There are other syntactical differences.
This is best solved by a module which converts between Lua and JSON representation. Take a look at the Lua wiki on JSON modules and find a Lua module to convert Lua to JSON. There are multiple modules, some which are pure Lua, being a good choice to embed into WoW. They correctly detect whether a table represents an array or dictionary and output the relevant JSON.
Solution 2:[2]
It can be converted steadily by syntactic parsing. However, this is a very tedious process.
$(function () {
$("#run").on("click", function () {
let src = $("#src").val();
let [i, contents] = convert(src, 0, []);
function isValue(element){
let idx = contents.indexOf(element) + 1
for(let i=idx; i < contents.length; i++){
if(["SPACE","TAB","RETURN"].indexOf(contents[i].type) > -1) continue;
if(contents[i].type == "SPLIT") return 0
if(contents[i].type == "BRKT_F") return 2
if(["BRKT_S","BRKT_W","BREAK","FBREAK"].indexOf(contents[i].type) > -1) return 1
}
}
let converted = "";
contents.forEach((element, index) => {
switch(element.type){
case "NUMBER":{
converted += element.content
break;
}
case "UNKNOWN": {
if(isValue(element)==1){
if(element.content == "return"){
} else if(["true","false"].indexOf(element.content)>-1){
converted += element.content
} else {
converted += '"' + element.content + '"'
}
} else if(isValue(element)==2){
converted += element.content
} else {
converted += '"' + element.content + '"'
}
break;
}
case "STR_S":
case "STR_D":{
converted += element.content
break;
}
case "BRKT_S":{
converted += element.content
break;
}
case "BRKT_W":{
converted += element.content
break;
}
case "BRKT_F":{
converted += element.content
break;
}
case "SPACE":{
converted += element.content
break;
}
case "TAB":{
converted += element.content
break;
}
case "RETURN":{
converted += element.content
break;
}
case "BREAK":{
converted += ","
break;
}
case "FBREAK":{
converted += "."
break;
}
case "SPLIT":{
converted += ":"
break;
}
}
});
$("#result").val(converted)
})
})
function getBracketSurfaceInner(contents, element){
if(["BRKT_S", "BRKT_W", "BRKT_F"].indexOf(element.type) == -1 || "]})".indexOf(element.content) == -1) return "";
let idx = contents.indexOf(element)
let innerElements = [];
let nest = 1;
for(let i=idx-1; i>=1; i--){
if(["BRKT_S", "BRKT_W", "BRKT_F" ].indexOf(contents[i].type)>=0){
if("]})".indexOf(contents[i].content)>=0){ nest ++ }
if("[{(".indexOf(contents[i].content)>=0){ nest -- }
}
if(nest==0 && contents[i].type == element.type){
return innerElements;
}
if(nest == 1) {
innerElements.unshift(contents[i]);
}
}
return innerElements;
}
function removeLastCamma(contents, element){
let idx = contents.indexOf(element)
let last = -1;
for(let i=idx-1; i>=1; i--){
if(["NUMBER", "UNKNOWN", "STR_S", "STR_D"].indexOf(contents[i].type)>=0) return;
if(contents[i].type == "BREAK"){
last = i;
break;
}
}
contents.splice(last, 1);
}
function convert(text, pos, contents) {
let MODE = undefined;
// NUMBER
// UNKNOWN
// SPLIT
// BREAK
// FBREAK
// STR_S
// STR_D
// BRKT_S
// BRKT_W
// BRKT_F
// CTRL
// RETURN
let MODES = [MODE];
let content = "", currentElement;
let i, c
function PUSH_BEFORE(replace) {
if (content.length > 1) {
contents.push({
type: MODE,
content: content.slice(0, content.length - 1),
});
}
content = "" + (replace ? replace : c)
currentElement = contents[contents.length-1];
MODE = MODES.shift()
}
function PUSH_AFTER(replace) {
if (content.length > 0) {
let str = (replace ? content.slice(0, content.length - 1) + replace : content.slice(0, content.length));
contents.push({
type: MODE,
content: str,
});
}
content = ""
currentElement = contents[contents.length-1];
MODE = MODES.shift()
}
for (i = pos; i < text.length; i++) {
c = text.charAt(i)
content = content + c
if (MODE == "ESCAPE") {
MODE = MODES.shift()
} else
if (MODE == "STR_S") {
if (c == "'") {
PUSH_AFTER('"')
}
} else
if (MODE == "STR_D") {
if (c == '"') {
PUSH_AFTER()
}
} else
if (MODE == "BRKT_S") {
if (c == ']') {
PUSH_BEFORE()
}
} else
if (MODE == "BRKT_F") {
if (c == ')') {
PUSH_BEFORE()
}
} else
if (MODE == "BRKT_W") {
if (c == '}') {
PUSH_BEFORE()
}
} else {
switch (c) {
case "{":{
PUSH_BEFORE()
MODE = "BRKT_W"
let begin_idx = contents.length;
contents.push({
type: MODE,
content: c,
});
MODES.push(MODE)
let [f, innerContents] = convert.call(this, text, i + 1, contents)
removeLastCamma(contents, contents[contents.length-1]);
let surface = getBracketSurfaceInner(innerContents, innerContents[innerContents.length-1]);
let d = 0;
for(let l=0; l<surface.length; l++){
if(surface[l].type == "SPLIT") { d = 1; break; }
}
i = f
content = ""
if(d==0){
contents[begin_idx].type = "BRKT_S";
contents[begin_idx].content = "[";
contents[contents.length-1].type = "BRKT_S";
contents[contents.length-1].content = "]";
MODE = MODES.shift() | "BRKT_S"
} else {
MODE = MODES.shift() | "BRKT_W"
}
break;
}
case "}":{
PUSH_BEFORE()
contents.push({
type: "BRKT_W",
content: c,
});
return [i, contents]
break;
}
case "[": {
PUSH_BEFORE()
MODE = "BRKT_S"
let begin_idx = contents.length;
contents.push({
type: MODE,
content: c,
});
MODES.push(MODE)
let [f, innerContents] = convert.call(this, text, i + 1, contents)
removeLastCamma(contents, contents[contents.length-1]);
innerContents = getBracketSurfaceInner(contents, contents[contents.length-1]);
let d = 0;
for(let l=0; l<innerContents.length; l++){
if(["BREAK", "BRKT_F"].indexOf(innerContents[l].type)>-1) {d = 1; break; }
}
if(d==0){
contents[begin_idx].type = "NOP";
contents[begin_idx].content = "";
contents[contents.length-1].type = "NOP";
contents[contents.length-1].content = "";
}
i = f
content = ""
MODE = MODES.shift() | "BRKT_S"
break;
}
case "]": {
PUSH_BEFORE()
contents.push({
type: "BRKT_S",
content: c,
});
return [i, contents]
break;
}
case "(": {
PUSH_BEFORE()
MODE = "BRKT_F"
let begin_idx = contents.length;
contents.push({
type: MODE,
content: c,
});
MODES.push(MODE)
let [f, innerContents] = convert.call(this, text, i + 1, contents)
removeLastCamma(contents, contents[contents.length-1]);
innerContents = getBracketSurfaceInner(contents, contents[contents.length-1]);
contents[begin_idx].type = "BRKT_F";
contents[begin_idx].content = "(";
contents[contents.length-1].type = "BRKT_F";
contents[contents.length-1].content = ")";
i = f
content = ""
MODE = MODES.shift() | "BRKT_F"
break;
}
case ")": {
PUSH_BEFORE()
contents.push({
type: "BRKT_F",
content: c,
});
return [i, contents]
break;
}
case "'": {
if(MODE=="STR_D") {
break;
}
PUSH_BEFORE('"')
MODE = "STR_S"
break;
}
case '"': {
if(MODE=="STR_S") {
break;
}
PUSH_BEFORE()
MODE = "STR_D"
break;
}
case "\\": {
MODES.push(MODE)
MODE = "ESCAPE"
break;
}
case ",": {
PUSH_BEFORE()
MODE = "BREAK"
break;
}
case ".": {
PUSH_BEFORE()
MODE = "FBREAK"
break;
}
case "=": {
PUSH_BEFORE(":")
MODE = "SPLIT"
break;
}
case ":": {
PUSH_BEFORE()
MODE = "SPLIT"
break;
}
case " ": {
if (MODE != "SPACE") {
PUSH_BEFORE()
MODE = "SPACE"
}
break;
}
case "\t": {
if (MODE != "TAB") {
PUSH_BEFORE()
MODE = "TAB"
}
break;
}
case "\n": {
PUSH_BEFORE()
MODE = "RETURN"
break;
}
default: {
if (" SPACE TAB RETURN BREAK FBREAK SPLIT ".indexOf(" " + MODE + " ") > -1) {
PUSH_BEFORE()
}
if (!isNaN(content)) {
MODE = "NUMBER"
}
else {
MODE = "UNKNOWN"
}
break;
}
}
}
}
return [i, contents]
}#src {
width: 400px;
height: 200px;
}
#result {
width: 400px;
height: 200px;
}<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
Source:<br><textarea id="src"></textarea>
<button id="run">Convert</button><br>
Result:<br><textarea id="result"></textarea>Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | Michal Kottman |
| Solution 2 | Stiffels |