Google-Apps-Script Convert XML to JSON - google-apps-script

I've got an XML string, like this:
'<ALEXA VER="0.9" URL="davidwalsh.name/" HOME="0" AID="="><SD TITLE="A" FLAGS="" HOST="davidwalsh.name"><TITLE TEXT="David Walsh Blog :: PHP, MySQL, CSS, Javascript, MooTools, and Everything Else"/><LINKSIN NUM="1102"/><SPEED TEXT="1421" PCT="51"/></SD><SD><POPULARITY URL="davidwalsh.name/" TEXT="7131"/><REACH RANK="5952"/><RANK DELTA="-1648"/></SD></ALEXA>'
I'd like to convert it into JSON format:
{
"ALEXA":{
"#attributes":{
"VER":"0.9",
"URL":"davidwalsh.name/",
"HOME":"0",
"AID":"="
},
"SD":[
{
"#attributes":{
"TITLE":"A",
"FLAGS":"",
"HOST":"davidwalsh.name"
},
"TITLE":{
"#attributes":{
"TEXT":"David Walsh Blog :: PHP, MySQL, CSS, Javascript, MooTools, and Everything Else"
}
...
I've found lot's of solutions for js, but none of them worked in google-apps-script.
I've also seen this question:
Parsing XML on a Google Apps script
but it does not exactly my case: I'de like to parse any XML into JSON, not just the provided sample.
I've found own solution (in the answer), and not sure it matches all cases.

I thought the solution should be a recursion function. After some research, I've found this great code by David Walsh and was able to adopt it. Here's what I've come to:
// Changes XML to JSON
// Original code: https://davidwalsh.name/convert-xml-json
function xmlToJson_(xml) {
// Create the return object
var obj = {};
// get type
var type = '';
try { type = xml.getType(); } catch(e){}
if (type == 'ELEMENT') {
// do attributes
var attributes = xml.getAttributes();
if (attributes.length > 0) {
obj["#attributes"] = {};
for (var j = 0; j < attributes.length; j++) {
var attribute = attributes[j];
obj["#attributes"][attribute.getName()] = attribute.getValue();
}
}
} else if (type == 'TEXT') {
obj = xml.getValue();
}
// get children
var elements = [];
try { elements = xml.getAllContent(); } catch(e){}
// do children
if (elements.length > 0) {
for(var i = 0; i < elements.length; i++) {
var item = elements[i];
var nodeName = false;
try { nodeName = item.getName(); } catch(e){}
if (nodeName)
{
if (typeof(obj[nodeName]) == "undefined") {
obj[nodeName] = xmlToJson_(item);
} else {
if (typeof(obj[nodeName].push) == "undefined") {
var old = obj[nodeName];
obj[nodeName] = [];
obj[nodeName].push(old);
}
obj[nodeName].push(xmlToJson_(item));
}
}
}
}
return obj;
};
I've posted the sample on GitHub.
Usage:
var xml = XmlService.parse(xmltext);
Logger.log(JSON.stringify(xmlToJson_(xml)));
Reference:
XmlService

The original answer didn't work for me. There may have been a change in the apps script XML API but it wouldn't include the text content of a node without children. Here is the code I wrote that seems to work well.
Note, it outputs in a slightly different fashion than the example you provided. I found that this might be a more consistent format for a broader range of use cases. I also found that including the attributes wasn't necessary for everything I was doing and created clutter, so I've included a version that doesn't parse attributes.
If you include attributes, the output follows this pattern:
{foo:{attributes:{...},content:{...}}
To Include Attributes:
function xmlParse(element) {
/*
* Takes an XML element and returns an object containing its children or text
* If children are present, recursively calls xmlTest() on them
*
* If multiple children share a name, they are added as objects in an array
* If children have unique names, they are simply added as keys
* i.e.
* <foo><bar>one</bar><baz>two</baz></foo> === {foo: {bar: 'one', baz: 'two'}}
* <foo><bar>one</bar><bar>two</bar></foo> === {foo: [{bar: 'one'},{bar: 'two'}]}
*/
let obj = {}
const rootName = element.getName();
// Parse attributes
const attributes = element.getAttributes();
const attributesObj = {};
for(const attribute of attributes) {
attributesObj[attribute.getName()] = attribute.getValue();
}
obj[rootName] = {
attributes: attributesObj,
content: {}
}
const children = element.getChildren();
const childNames = children.map(child => child.getName());
if (children.length === 0) {
// Base case - get text content if no children
obj = {
content: element.getText(),
attributes: attributesObj
}
} else if (new Set(childNames).size !== childNames.length) {
// If nonunique child names, add children as an array
obj[rootName].content = [];
for (const child of children) {
if (child.getChildren().length === 0) {
const childObj = {};
childObj[child.getName()] = xmlParse(child);
obj[rootName].content.push(childObj)
} else {
const childObj = xmlParse(child);
obj[rootName].content.push(childObj)
}
}
} else {
// If unique child names, add children as keys
obj[rootName].content = {};
for (const child of children) {
if (child.getChildren().length === 0) {
obj[rootName].content[child.getName()] = xmlParse(child);
} else {
obj[rootName].content = xmlParse(child);
}
}
}
return obj;
}
Without Attributes:
function xmlParse(element) {
/*
* Takes an XML element and returns an object containing its children or text
* If children are present, recursively calls xmlTest() on them
*
* If multiple children share a name, they are added as objects in an array
* If children have unique names, they are simply added as keys
* i.e.
* <foo><bar>one</bar><baz>two</baz></foo> === {foo: {bar: 'one', baz: 'two'}}
* <foo><bar>one</bar><bar>two</bar></foo> === {foo: [{bar: 'one'},{bar: 'two'}]}
*/
let obj = {}
const rootName = element.getName();
const children = element.getChildren();
const childNames = children.map(child => child.getName());
if (children.length === 0) {
// Base case - get text content if no children
obj = element.getText();
} else if (new Set(childNames).size !== childNames.length) {
// If nonunique child names, add children as an array
obj[rootName] = [];
for (const child of children) {
if (child.getChildren().length === 0) {
const childObj = {};
childObj[child.getName()] = xmlParse(child);
obj[rootName].push(childObj)
} else {
const childObj = xmlParse(child);
obj[rootName].push(childObj)
}
}
} else {
// If unique child names, add children as keys
obj[rootName] = {};
for (const child of children) {
if (child.getChildren().length === 0) {
obj[rootName][child.getName()] = xmlParse(child);
} else {
obj[rootName] = xmlParse(child);
}
}
}
return obj;
}
Usage for both of these:
const xml = XmlService.parse(xmlText);
const rootElement = xml.getRootElement();
const obj = xmlParse(rootElement);
const asJson = JSON.stringify(obj);
Reference:
XMLService

Related

Autodesk-XLSExtension, undefined viewer

Im trying to implement the XLS Extension. In the ModelData class, i cannot get objects leaf nodes because the viewer is undefined.
Here is the problematic method:
getAllLeafComponents(callback) {
// from https://learnforge.autodesk.io/#/viewer/extensions/panel?id=enumerate-leaf-nodes
viewer.getObjectTree(function (tree) {
let leaves = [];
tree.enumNodeChildren(tree.getRootId(), function (dbId) {
if (tree.getChildCount(dbId) === 0) {
leaves.push(dbId);
}
}, true);
callback(leaves);
});
}
Im getting Cannot read properties of undefined (reading 'getObjectTree') , meaning viewer is undefined.
However, viewer is working and displaying documents.
I tried to call it by window.viewer and this.viewer to no avail.
Thanks in advance for any help
It looks like it missed two lines. Could you try the revised one below?
// Model data in format for charts
class ModelData {
constructor(viewer) {
this._modelData = {};
this._viewer = viewer;
}
init(callback) {
var _this = this;
var viewer = _this._viewer;
_this.getAllLeafComponents(function (dbIds) {
var count = dbIds.length;
dbIds.forEach(function (dbId) {
viewer.getProperties(dbId, function (props) {
props.properties.forEach(function (prop) {
if (!isNaN(prop.displayValue)) return; // let's not categorize properties that store numbers
// some adjustments for revit:
prop.displayValue = prop.displayValue.replace('Revit ', ''); // remove this Revit prefix
if (prop.displayValue.indexOf('<') == 0) return; // skip categories that start with <
// ok, now let's organize the data into this hash table
if (_this._modelData[prop.displayName] == null) _this._modelData[prop.displayName] = {};
if (_this._modelData[prop.displayName][prop.displayValue] == null) _this._modelData[prop.displayName][prop.displayValue] = [];
_this._modelData[prop.displayName][prop.displayValue].push(dbId);
})
if ((--count) == 0) callback();
});
})
})
}
getAllLeafComponents(callback) {
var _this = this;
var viewer = _this._viewer;
// from https://learnforge.autodesk.io/#/viewer/extensions/panel?id=enumerate-leaf-nodes
viewer.getObjectTree(function (tree) {
var leaves = [];
tree.enumNodeChildren(tree.getRootId(), function (dbId) {
if (tree.getChildCount(dbId) === 0) {
leaves.push(dbId);
}
}, true);
callback(leaves);
});
}
hasProperty(propertyName){
return (this._modelData[propertyName] !== undefined);
}
getLabels(propertyName) {
return Object.keys(this._modelData[propertyName]);
}
getCountInstances(propertyName) {
return Object.keys(this._modelData[propertyName]).map(key => this._modelData[propertyName][key].length);
}
getIds(propertyName, propertyValue) {
return this._modelData[propertyName][propertyValue];
}
}

Get the first hyperlink and its text value

I hope everyone is in good health health and condition.
Recently, I have been working on Google Docs hyperlinks using app scripts and learning along the way. I was trying to get all hyperlink and edit them and for that I found an amazing code from this post. I have read the code multiple times and now I have a good understanding of how it works.
My confusion
My confusion is the recursive process happening in this code, although I am familiar with the concept of Recursive functions but when I try to modify to code to get only the first hyperlink from the document, I could not understand it how could I achieve that without breaking the recursive function.
Here is the code that I am trying ;
/**
* Get an array of all LinkUrls in the document. The function is
* recursive, and if no element is provided, it will default to
* the active document's Body element.
*
* #param {Element} element The document element to operate on.
* .
* #returns {Array} Array of objects, vis
* {element,
* startOffset,
* endOffsetInclusive,
* url}
*/
function getAllLinks(element) {
var links = [];
element = element || DocumentApp.getActiveDocument().getBody();
if (element.getType() === DocumentApp.ElementType.TEXT) {
var textObj = element.editAsText();
var text = element.getText();
var inUrl = false;
for (var ch=0; ch < text.length; ch++) {
var url = textObj.getLinkUrl(ch);
if (url != null) {
if (!inUrl) {
// We are now!
inUrl = true;
var curUrl = {};
curUrl.element = element;
curUrl.url = String( url ); // grab a copy
curUrl.startOffset = ch;
}
else {
curUrl.endOffsetInclusive = ch;
}
}
else {
if (inUrl) {
// Not any more, we're not.
inUrl = false;
links.push(curUrl); // add to links
curUrl = {};
}
}
}
if (inUrl) {
// in case the link ends on the same char that the element does
links.push(curUrl);
}
}
else {
var numChildren = element.getNumChildren();
for (var i=0; i<numChildren; i++) {
links = links.concat(getAllLinks(element.getChild(i)));
}
}
return links;
}
I tried adding
if (links.length > 0){
return links;
}
but it does not stop the function as it is recursive and it return back to its previous calls and continue running.
Here is the test document along with its script that I am working on.
https://docs.google.com/document/d/1eRvnR2NCdsO94C5nqly4nRXCttNziGhwgR99jElcJ_I/edit?usp=sharing
I hope you will understand what I am trying to convey, Thanks for giving a look at my post. Stay happy :D
I believe your goal as follows.
You want to retrieve the 1st link and the text of link from the shared Document using Google Apps Script.
You want to stop the recursive loop when the 1st element is retrieved.
Modification points:
I tried adding
if (links.length > 0){
return links;
}
but it does not stop the function as it is recursive and it return back to its previous calls and continue running.
About this, unfortunately, I couldn't understand where you put the script in your script. In this case, I think that it is required to stop the loop when links has the value. And also, it is required to also retrieve the text. So, how about modifying as follows? I modified 3 parts in your script.
Modified script:
function getAllLinks(element) {
var links = [];
element = element || DocumentApp.getActiveDocument().getBody();
if (element.getType() === DocumentApp.ElementType.TEXT) {
var textObj = element.editAsText();
var text = element.getText();
var inUrl = false;
for (var ch=0; ch < text.length; ch++) {
if (links.length > 0) break; // <--- Added
var url = textObj.getLinkUrl(ch);
if (url != null) {
if (!inUrl) {
// We are now!
inUrl = true;
var curUrl = {};
curUrl.element = element;
curUrl.url = String( url ); // grab a copy
curUrl.startOffset = ch;
}
else {
curUrl.endOffsetInclusive = ch;
}
}
else {
if (inUrl) {
// Not any more, we're not.
inUrl = false;
curUrl.text = text.slice(curUrl.startOffset, curUrl.endOffsetInclusive + 1); // <--- Added
links.push(curUrl); // add to links
curUrl = {};
}
}
}
if (inUrl) {
// in case the link ends on the same char that the element does
links.push(curUrl);
}
}
else {
var numChildren = element.getNumChildren();
for (var i=0; i<numChildren; i++) {
if (links.length > 0) { // <--- Added or if (links.length > 0) break;
return links;
}
links = links.concat(getAllLinks(element.getChild(i)));
}
}
return links;
}
In this case, I think that if (links.length > 0) {return links;} can be modified to if (links.length > 0) break;.
Note:
By the way, when Google Docs API is used, both the links and the text can be also retrieved by a simple script as follows. When you use this, please enable Google Docs API at Advanced Google services.
function myFunction() {
const doc = DocumentApp.getActiveDocument();
const res = Docs.Documents.get(doc.getId()).body.content.reduce((ar, {paragraph}) => {
if (paragraph && paragraph.elements) {
paragraph.elements.forEach(({textRun}) => {
if (textRun && textRun.textStyle && textRun.textStyle.link) {
ar.push({text: textRun.content, url: textRun.textStyle.link.url});
}
});
}
return ar;
}, []);
console.log(res) // You can retrieve 1st link and test by console.log(res[0]).
}

html, css and pure js for tree view

This is quite simple but I'm quite new with JavaScript. Here is the problem I'm facing.
I would like to have this tree view:
Route (index.html)
|--Tree 1 (tree1.html)
|--Child 1 (tree1child1.html)
|--Tree 2 (tree2.html)
|--Child 1 (tree2child1.html)
Each html will point to toggle.js to generate the tree view. My problem with the .js is: if I click on the Tree 2, Child 1 - it will show the correct page but pointing to the Tree 1, Child 1 selections as the child has same name. This is the script that I use.
function toggle(id) {
ul = "ul_" + id;
img = "img_" + id;
ulElement = document.getElementById(ul);
imgElement = document.getElementById(img);
if (ulElement) {
if (ulElement.className == 'closed') {
ulElement.className = "open";
imgElement.src = "./menu/opened.gif";
} else {
ulElement.className = "closed";
imgElement.src = "./menu/closed.gif";
}
}
} // toggle()
function searchUp(element, tagName) {
// look through the passed elements
var current = element;
do {
current = current.parentNode;
} while (current.nodeName != tagName.toUpperCase() && current.nodeName != "BODY");
return current.nodeName != tagName.toUpperCase() ? null : current;
}
function getAnchor(elements, searchText, exclude) {
// look through the passed elements
for (var i = 0; i < elements.length; i++) {
if (elements[i].innerHTML == searchText) {
if (exclude == null || exclude.innerHTML != elements[i].parentElement.innerHTML) {
// return the anchor tag
return elements[i];
}
}
if (elements[i].children != null) {
var a = getAnchor(elements[i].children, searchText, exclude);
if (a != null) {
return a;
}
}
}
return null;
}
function htmlEntities(str) {
return String(str).replace(/&/g, '&').replace(/</g, '<').replace(/>/g, '>').replace(/"/g, '"');
}
function select(tree) {
// NOTE: we need to escape the tree string to replace chevrons with their html equivalent in order to match generic strings correctly
var items = document.getElementById('menu').children; // .getElementsByTagName("a");
var anchor = getAnchor(items, htmlEntities(tree[0]), null);
var ul = searchUp(anchor, "ul");
for (var i = 1; i < tree.length; i++) {
anchor = getAnchor(ul.children, htmlEntities(tree[i]), anchor.parentElement);
ul = searchUp(anchor, "ul");
}
if (anchor != null) {
anchor.className = 'selected';
if (ul.className != 'open') {
toggle(ul.id.substr(3));
}
}
} // select()

How to pass a whole dojox.grid.DataGrid store(items json data) to servlet?

I have a button on page - when clicked, it passes all the data to the servlet that could update each row data. My question is how to pass the whole store to the servlet as json data? Is there any easy way? Thanks
Here is some code I wrote to get the store to an object. Then it can be converted to JSON using dojo.toJson(obj);. I learned about this from the dojotoolkit website originally. (Give credit where credit is due). I realize this code is huge and nasty. When I looked for a better way about a year back I could not find one.
JsonHelper.storeToObject = function(store) {
var object = [];
var index = -1;
store.fetch({
onItem : function(item, request) {
object[++index] = JsonHelper.itemToObject(store, item);
}
});
return object;
};
JsonHelper.itemToObject = function(store, item) {
// store:
// The datastore the item came from.
// item:
// The item in question.
var obj = {};
if (item && store) {
// Determine the attributes we need to process.
var attributes = store.getAttributes(item);
if (attributes && attributes.length > 0) {
var i;
for (i = 0; i < attributes.length; i++) {
var values = store.getValues(item, attributes[i]);
if (values) {
// Handle multivalued and single-valued attributes.
if (values.length > 1) {
var j;
obj[attributes[i]] = [];
for (j = 0; j < values.length; j++) {
var value = values[j];
// Check that the value isn't another item. If
// it is, process it as an item.
if (store.isItem(value)) {
obj[attributes[i]].push(itemToObject(store,
value));
} else {
obj[attributes[i]].push(value);
}
}
} else {
if (store.isItem(values[0])) {
obj[attributes[i]] = itemToObject(store,
values[0]);
} else {
obj[attributes[i]] = values[0];
}
}
}
}
}
}
return obj;
};

Trying to create a function which extracts a URL from an array. JavaScript

So basically I would like to create a function that when alerted, returns the URL from an array (in this case the array is declared as 'websites'). The function has two parameters 'websites' and 'searchTerm'.
I'm struggling to make the function behave, so that when i type yahoo or google or bing in the searchTerm parameter for the function; I want it to return the corresponding URL.
Any help or support would be greatly appreciated.
Sorry if I have not made myself clear in my explanation, if this is the case, let me know and I will try and be clearer in my explanation.
Thanks in advance!
Try something more like:
var websites = {google: 'www.google.com', yahoo: 'www.yahoo.com'};
function filterURL(websites,searchTerm)
{
return websites[searchTerm] || 'www.defaultsearchwebstirehere.com';
}
** Update following comment **
Build up your websites object like so (where input is your array of key values seperated by pipe characters):
var websites = {};
for (var i = 0; i < input.length; i++) {
var siteToSearchTerm = input[i].split('|');
websites[siteToSearchTerm[1]] = siteToSearchTerm[0];
}
Here is how:
var websites = ["www.google.com|Google" , "www.yahoo.com|Yahoo" , "www.bing.com|Bing"];
function filterURL(websites,searchTerm)
{
for (var i = 0; i < websites.length; i++) {
if (websites[i].split('|')[1] === searchTerm) {
return websites[i].split('|')[0];
}
}
}
Working Example
You can also validate and improve function:
function filterURL(websites,searchTerm)
{
if (typeof websites != 'Array' || ! searchTerm) return false;
for (var i = 0; i < websites.length; i++) {
if (websites[i].split('|')[1] === searchTerm) {
return websites[i].split('|')[0];
}
}
return false;
}
Why not just use an object?
var websites = {
Google: 'www.google.com',
Yahoo: 'www.yahoo.com'
};
function filterURL(sites, searchTerm) {
if (sites[searchTerm]) {
return sites[searchTerm];
} else {
// What do you want to do when it can't be found?
}
}
alert(filterURL(websites, 'Google')); // alerts 'www.google.com'
You should really be using a hash-table like structure so that you don't have to search through the whole array every time. Something like this:
var websites = {
"Google": "www.google.com",
"Yahoo": "www.yahoo.com",
"Bing": "www.bing.com"
};
function filterURL(websites, searchTerm) {
if (websites[searchTerm] !== undefined)
return websites[searchTerm];
else
return null;
}
I'm not sure why you want to use an array for this, as what you're really doing fits a key-value pair better; however, here's how I'd do it:
function filterURL(websites, searchTerm) {
var i = 0,
parts;
for (i = 0; i < websites.length; i++) {
parts = websites[i].split("|");
if (parts[1].toLowerCase() === searchTerm) {
return parts[0];
}
}
}
But consider if you used a proper JavaScript Object instead:
var websites = {
Google: "www.google.com",
Yahoo: "www.yahoo.com",
Bing: "www.bing.com"
}
// Now it's much simpler:
function filterURL(websites, searchTerm) {
// key has first letter capitalized…
return websites[searchTerm.charAt(0).toUpperCase() + searchTerm.slice(1).toLowerCase()];
}