I am working on a language that transpiles to javascript and has a similar syntax. However I want to include some new type of block statements. For syntax purposes they are the same as an IfStatement. How can I get esprima or acorn to parse this program MyStatement {a=1;} without throwing an error? Its fine if it calls it an IfStatement. I would prefer not to fork esprima.
It turns out, that the plugin capabilities of acorn are not really documented. It seems like forking acorn would be the easiest route. In this case, it is as simple as searching for occurances of _if and following a similar pattern for _MyStatement.
However it is possible to write a plugin to accomplish what I was trying to do. It seems a bit of a hack, but here is the code. The basic steps are:
To exend Parse and add to the list of keywords that will be recognized by the first pass
Create a TokenType for the new keyword and add it to the Parser.acorn.keywordTypes, extend parseStatement so that it processes the new TokenType
Create a handler for the new TokenType which will add information to the Abstract Syntax Tree as required by the keyword functionality and also consume tokens using commands like this.expect(tt.parenR) to eat a '(' or this.parseExpression() to process an entire expression.
Here is the code:
var program =
`
MyStatement {
MyStatement(true) {
MyStatement() {
var a = 1;
}
}
if (1) {
var c = 0;
}
}
`;
const acorn = require("acorn");
const Parser = acorn.Parser;
const tt = acorn.tokTypes; //used to access standard token types like "("
const TokenType = acorn.TokenType; //used to create new types of Tokens.
//add a new keyword to Acorn.
Parser.acorn.keywordTypes["MyStatement"] = new TokenType("MyStatement",{keyword: "MyStatement"});
//const isIdentifierStart = acorn.isIdentifierStart;
function wordsRegexp(words) {
return new RegExp("^(?:" + words.replace(/ /g, "|") + ")$")
}
var bruceware = function(Parser) {
return class extends Parser {
parse(program) {
console.log("hooking parse.");
//it appears it is necessary to add keywords here also.
var newKeywords = "break case catch continue debugger default do else finally for function if return switch throw try var while with null true false instanceof typeof void delete new in this const class extends export import super";
newKeywords += " MyStatement";
this.keywords = wordsRegexp(newKeywords);
return(super.parse(program));
}
parseStatement(context, topLevel, exports) {
var starttype = this.type;
console.log("!!!hooking parseStatement", starttype);
if (starttype == Parser.acorn.keywordTypes["MyStatement"]) {
console.log("Parse MyStatement");
var node = this.startNode();
return this.parseMyStatement(node);
}
else {
return(super.parseStatement(context, topLevel, exports));
}
}
parseMyStatement(node) {
console.log("parse MyStatement");
this.next();
//In my language, MyStatement doesn't have to have a parameter. It could be called as `MyStatement { ... }`
if (this.type == tt.parenL) {
node.test = this.parseOptionalParenExpression();
}
else {
node.test = 0; //If there is no test, just make it 0 for now (note that this may break code generation later).
}
node.isMyStatement = true; //set a flag so we know that this if a "MyStatement" instead of an if statement.
//process the body of the block just like a normal if statement for now.
// allow function declarations in branches, but only in non-strict mode
node.consequent = this.parseStatement("if");
//node.alternate = this.eat(acornTypes["else"]) ? this.parseStatement("if") : null;
return this.finishNode(node, "IfStatement")
};
//In my language, MyStatement, optionally has a parameter. It can also by called as MyStatement() { ... }
parseOptionalParenExpression() {
this.expect(tt.parenL);
//see what type it is
console.log("Type: ", this.type);
//allow it to be blank.
var val = 0; //for now just make the condition 0. Note that this may break code generation later.
if (this.type == tt.parenR) {
this.expect(tt.parenR);
}
else {
val = this.parseExpression();
this.expect(tt.parenR);
}
return val
};
}
}
process.stdout.write('\033c'); //cls
var result2 = Parser.extend(bruceware).parse(program); //attempt to parse
console.log(JSON.stringify(result2,null,' ')); //show the results.
How do I call a simple addition function and assert the result of two values using selenium-cucumber-js framework with a test written below. While running the below it says
TypeError: TypeError: Cannot read property 'addvalues' of undefined
at createWorld.When (C:\Tests\cucumber\step-definitions\addvalues-steps.js:5:25)
Feature:
Scenario: Addition of two values
When Add two values 5 and 10
Then I should get result 15
// Here is my 'addvalues-steps.js' file
const expect = require('chai').expect;
module.exports = function () {
this.When(/^Add two values (-?\d+) and (-?\d+)$/, (x, y) =>{
this.page.addvalues.addValues(x,y);
})
this.Then(/^I should get result (-?\d+)$/, (ans) =>{
let tot = this.page.addvalues.addValues(x, y);
expect(tot).to.be.eql(ans);
})
};
// Following is my 'addvalues.js file'
module.exports = {
addValues(x,y){
var total = x + y ;
return total ;
}
};
// world.js >>
const { CustomWorld } = require('cucumber')
function CustomWorld() {
console.log('overriding the world')
this.page = {
addvalues: require('../page-objects/addvalues')
}
console.log("This is the recent error log:"+this.page.addvalues)
}
module.exports = function() {
this.World = CustomWorld;
Note: the below example is for an old version of cucumber-js: 1.3.3.
With cucumber.js, when you're referencing this from inside step definitions, you're actually referencing the World context. So, for this.page.addvalues.addValues(x,y); to work properly, you'll first need to create page that has a reference to your addvalues.js. Something along these lines:
world.js:
function CustomWorld() {
console.log('overriding the world')
this.page = {
addvalues: require('../page-objects/addvalues')
}
}
module.exports = function() {
this.World = CustomWorld;
};
addvalues.js:
//addvalues.js
module.exports = {
addValues(x,y){
var total = x + y ;
return total ;
}
};
There's also a couple of things to correct in your steps.js.
Don't pass arrow functions into the steps, as this will remove the this context that you're setting in World.js.
If you want to share variables between steps (as you do in your example), you need to store them somewhere. One such place, again, would be the World context. Note how in my version I set this.prevResult
When the variables are injected into your steps, they are injected as strings. Note the parseInt() in my version.
addvalues-steps.js:
const expect = require('chai').expect;
module.exports = function() {
this.When(/^Add two values (-?\d+) and (-?\d+)$/, function (x, y) {
this.prevResult = this.page.addvalues.addValues(parseInt(x, 10), parseInt(y, 10));
})
this.Then(/^I should get result (-?\d+)$/, function (ans) {
let tot = this.prevResult;
expect(tot).to.be.eql(parseInt(ans, 10));
})
}
UPD: It turns out that the question is about selenium-cucumber-js, which is a framework on top of cucumber-js. Disregard the comments about the world.js.
According to selenium-cucumber-js docs, you don't need this to access the page objects in your step definitions:
Page objects are accessible via a global page object and are
automatically loaded from ./page-objects.
const expect = require('chai').expect;
module.exports = function() {
this.When(/^Add two values (-?\d+) and (-?\d+)$/, function (x, y) {
this.prevResult = page.addvalues.addValues(parseInt(x, 10), parseInt(y, 10));
})
this.Then(/^I should get result (-?\d+)$/, function (ans) {
let tot = this.prevResult;
expect(tot).to.be.eql(parseInt(ans, 10));
})
}
I'm working on this assignment: http://www.cs.colostate.edu/~anderson/ct310/index.html/doku.php?id=assignments:assignment_2
I'm building a binary tree in Javascript. Basically it's a relational tree, we have this tree class that takes 3 arguments: data,left child,right child. Left & right child are just new tree objects stored in var.
Here's the tree class:
function Tree( data, left, right )
{
// pravite data
var data = data;
var leftChild = left;
var rightChild = right;
// public functions
this.getData = function()
{
return data;
}
this.left = function()
{
return leftChild;
}
this.right = function()
{
return rightChild;
}
}
Here's the toString() method
Tree.prototype.toString = function(indent)
{
var spaces = '';
if (!indent)
{
indent = 0;
}
else{
spaces = spaces*indent;
}
// if the left tree isn't void
if(this.tree().left())
{
this.tree().left().toString(indent+5);
}
if(this.tree().right())
{
this.tree.right().toString(indent+5);
}
print(spaces + this.data);
}
Here's the data I get passed into. We're using Rhino in the command line to test.
var abc = new Tree('a', new Tree('b'), new Tree('c'));
abc.toString()
I get a stack over flow on the toString method. My professor says to use the this.Left() in the if statement because when you recurse it will fail when it's undefined.
Any ideas what's wrong?
Well, your last reference to the right branch is missing some parentheses...
this.tree.right().toString(indent+5) // <-- right here
That asid, I don't see this.tree() defined anywhere. I think it should be this.left() and this.right() in all those places.
Also, for a slight optimisation, consider something like:
var l = this.left();
if( l) l.toString(indent+5);
This avoids an extra function call.
Your recursive function has no base case. It will just keep going forever.
If your node doesn't have any children, than don't call ToString on them()
I need to detect and eval the Javascript code contained in a string.
The following code works, but it only evaluates the first <script>...</script> it founds.
function executeJs(html) {
var scriptFragment = "<script(.+?)>(.+?)<\/script>";
match = new RegExp(scriptFragment, "im");
var matches = html.match(match);
if (matches.length >= 2) {
eval(matches[2]);
}
}
I wonder if there is a method that allows me to iterate and execute all Javascript fragments.
The reason it only takes the first one is because you're missing the g flag. Try this:
function executeJs(html) {
var scriptFragment = '<script(.*?)>(.+?)<\/script>';
var re = new RegExp(scriptFragment, 'gim'), match;
while ((match = re.exec(html)) != null) {
eval(match[2]);
}
}
executeJs('<script>alert("hello")</script>abc<script>alert("world")</script>');
Here is some code that does the same thing in a slightly different way. You can pass the string to the function and it will eval all the script tags and return the cleaned source(without script). There is also a slight difference in the way IE handles it, that is handled in the code as well, you may adapt it to your requirements. Also, the evaluated code has the global context. Hope it helps.
function parseScript(_source)
{
var source = _source;
var scripts = new Array();
// Strip out tags
while(source.indexOf("<script") > -1 || source.indexOf("</script") > -1)
{
var s = source.indexOf("<script");
var s_e = source.indexOf(">", s);
var e = source.indexOf("</script", s);
var e_e = source.indexOf(">", e);
// Add to scripts array
scripts.push(source.substring(s_e+1, e));
// Strip from source
source = source.substring(0, s) + source.substring(e_e+1);
}
// Loop through every script collected and eval it
for(var i=0; i<scripts.length; i++)
{
try
{
//eval(scripts[i]);
if(window.execScript)
{
window.execScript(scripts[i]); // IE
}
else
{
window.setTimeout(scripts[i],0); // Changed this from eval() to setTimeout() to get it in Global scope
}
}
catch(ex)
{
// do what you want here when a script fails
alert("Javascript Handler failed interpretation. Even I am wondering why(?)");
}
}
// Return the cleaned source
return source;
}
Blixt should be right...
You may also take a look at prototype's String.evalScripts function.
http://api.prototypejs.org/language/string.html#evalscripts-instance_method
Given a function, I'm trying to find out the names of the nested functions in it (only one level deep).
A simple regex against toString() worked until I started using functions with comments in them. It turns out that some browsers store parts of the raw source while others reconstruct the source from what's compiled; The output of toString() may contain the original code comments in some browsers. As an aside, here are my findings:
Test subject
function/*post-keyword*/fn/*post-name*/()/*post-parens*/{
/*inside*/
}
document.write(fn.toString());
Results
Browser post-keyword post-name post-parens inside
----------- ------------ --------- ----------- --------
Firefox No No No No
Safari No No No No
Chrome No No Yes Yes
IE Yes Yes Yes Yes
Opera Yes Yes Yes Yes
I'm looking for a cross-browser way of extracting the nested function names from a given function. The solution should be able to extract "fn1" and "fn2" out of the following function:
function someFn() {
/**
* Some comment
*/
function fn1() {
alert("/*This is not a comment, it's a string literal*/");
}
function // keyword
fn2 // name
(x, y) // arguments
{
/*
body
*/
}
var f = function () { // anonymous, ignore
};
}
The solution doesn't have to be pure regex.
Update: You can assume that we're always dealing with valid, properly nested code with all string literals, comments and blocks terminated properly. This is because I'm parsing a function that has already been compiled as a valid function.
Update2: If you're wondering about the motivation behind this: I'm working on a new JavaScript unit testing framework that's called jsUnity. There are several different formats in which you can write tests & test suites. One of them is a function:
function myTests() {
function setUp() {
}
function tearDown() {
}
function testSomething() {
}
function testSomethingElse() {
}
}
Since the functions are hidden inside a closure, there's no way for me invoke them from outside the function. I therefore convert the outer function to a string, extract the function names, append a "now run the given inner function" statement at the bottom and recompile it as a function with new Function(). If the test function have comments in them, it gets tricky to extract the function names and to avoid false positives. Hence I'm soliciting the help of the SO community...
Update3: I've come up with a new solution that doesn't require a lot of semantic fiddling with code. I use the original source itself to probe for first-level functions.
Cosmetic changes and bugfix
The regular expression must read \bfunction\b to avoid false positives!
Functions defined in blocks (e.g. in the bodies of loops) will be ignored if nested does not evaluate to true.
function tokenize(code) {
var code = code.split(/\\./).join(''),
regex = /\bfunction\b|\(|\)|\{|\}|\/\*|\*\/|\/\/|"|'|\n|\s+/mg,
tokens = [],
pos = 0;
for(var matches; matches = regex.exec(code); pos = regex.lastIndex) {
var match = matches[0],
matchStart = regex.lastIndex - match.length;
if(pos < matchStart)
tokens.push(code.substring(pos, matchStart));
tokens.push(match);
}
if(pos < code.length)
tokens.push(code.substring(pos));
return tokens;
}
var separators = {
'/*' : '*/',
'//' : '\n',
'"' : '"',
'\'' : '\''
};
function extractInnerFunctionNames(func, nested) {
var names = [],
tokens = tokenize(func.toString()),
level = 0;
for(var i = 0; i < tokens.length; ++i) {
var token = tokens[i];
switch(token) {
case '{':
++level;
break;
case '}':
--level;
break;
case '/*':
case '//':
case '"':
case '\'':
var sep = separators[token];
while(++i < tokens.length && tokens[i] !== sep);
break;
case 'function':
if(level === 1 || (nested && level)) {
while(++i < tokens.length) {
token = tokens[i];
if(token === '(')
break;
if(/^\s+$/.test(token))
continue;
if(token === '/*' || token === '//') {
var sep = separators[token];
while(++i < tokens.length && tokens[i] !== sep);
continue;
}
names.push(token);
break;
}
}
break;
}
}
return names;
}
The academically correct way to handle this would be creating a lexer and parser for a subset of Javascript (the function definition), generated by a formal grammar (see this link on the subject, for example).
Take a look at JS/CC, for a Javascript parser generator.
Other solutions are just regex hacks, that lead to unmaintainable/unreadable code and probably to hidden parsing errors in particular cases.
As a side note, I'm not sure to understand why you aren't specifying the list of unit test functions in your product in a different way (an array of functions?).
Would it matter if you defined your tests like:
var tests = {
test1: function (){
console.log( "test 1 ran" );
},
test2: function (){
console.log( "test 2 ran" );
},
test3: function (){
console.log( "test 3 ran" );
}
};
Then you could run them as easily as this:
for( var test in tests ){
tests[test]();
}
Which looks much more easier.
You can even carry the tests around in JSON that way.
I like what you're doing with jsUnity. And when I see something I like (and have enough free time ;)), I try to reimplement it in a way which better suits my needs (also known as 'not-invented-here' syndrome).
The result of my efforts is described in this article, the code can be found here.
Feel free to rip-out any parts you like - you can assume the code to be in the public domain.
The trick is to basically generate a probe function that will check if a given name is the name of a nested (first-level) function. The probe function uses the function body of the original function, prefixed with code to check the given name within the scope of the probe function. OK, this can be better explained with the actual code:
function splitFunction(fn) {
var tokens =
/^[\s\r\n]*function[\s\r\n]*([^\(\s\r\n]*?)[\s\r\n]*\([^\)\s\r\n]*\)[\s\r\n]*\{((?:[^}]*\}?)+)\}\s*$/
.exec(fn);
if (!tokens) {
throw "Invalid function.";
}
return {
name: tokens[1],
body: tokens[2]
};
}
var probeOutside = function () {
return eval(
"typeof $fn$ === \"function\""
.split("$fn$")
.join(arguments[0]));
};
function extractFunctions(fn) {
var fnParts = splitFunction(fn);
var probeInside = new Function(
splitFunction(probeOutside).body + fnParts.body);
var tokens;
var fns = [];
var tokenRe = /(\w+)/g;
while ((tokens = tokenRe.exec(fnParts.body))) {
var token = tokens[1];
try {
if (probeInside(token) && !probeOutside(token)) {
fns.push(token);
}
} catch (e) {
// ignore token
}
}
return fns;
}
Runs fine against the following on Firefox, IE, Safari, Opera and Chrome:
function testGlobalFn() {}
function testSuite() {
function testA() {
function testNested() {
}
}
// function testComment() {}
// function testGlobalFn() {}
function // comments
testB /* don't matter */
() // neither does whitespace
{
var s = "function testString() {}";
}
}
document.write(extractFunctions(testSuite));
// writes "testA,testB"
Edit by Christoph, with inline answers by Ates:
Some comments, questions and suggestions:
Is there a reason for checking
typeof $fn$ !== "undefined" && $fn$ instanceof Function
instead of using
typeof $fn$ === "function"
instanceof is less safe than using typeof because it will fail when passing objects between frame boundaries. I know that IE returns wrong typeof information for some built-in functions, but afaik instanceof will fail in these cases as well, so why the more complicated but less safe test?
[AG] There was absolutely no legitimate reason for it. I've changed it to the simpler "typeof === function" as you suggested.
How are you going to prevent the wrongful exclusion of functions for which a function with the same name exists in the outer scope, e.g.
function foo() {}
function TestSuite() {
function foo() {}
}
[AG] I have no idea. Can you think of anything. Which one is better do you think? (a) Wrongful exclusion of a function inside. (b) Wronfgul inclusion of a function outside.
I started to think that the ideal solution will be a combination of your solution and this probing approach; figure out the real function names that are inside the closure and then use probing to collect references to the actual functions (so that they can be directly called from outside).
It might be possible to modify your implementation so that the function's body only has to be eval()'ed once and not once per token, which is rather inefficient. I might try to see what I can come up with when I have some more free time today...
[AG] Note that the entire function body is not eval'd. It's only the bit that's inserted to the top of the body.
[CG] Your right - the function's body only gets parsed once during the creation of probeInside - you did some nice hacking, there ;). I have some free time today, so let's see what I can come up with...
A solution that uses your parsing method to extract the real function names could just use one eval to return an array of references to the actual functions:
return eval("[" + fnList + "]");
[CG] Here is with what I came up. An added bonus is that the outer function stays intact and thus may still act as closure around the inner functions. Just copy the code into a blank page and see if it works - no guarantees on bug-freelessness ;)
<pre><script>
var extractFunctions = (function() {
var level, names;
function tokenize(code) {
var code = code.split(/\\./).join(''),
regex = /\bfunction\b|\(|\)|\{|\}|\/\*|\*\/|\/\/|"|'|\n|\s+|\\/mg,
tokens = [],
pos = 0;
for(var matches; matches = regex.exec(code); pos = regex.lastIndex) {
var match = matches[0],
matchStart = regex.lastIndex - match.length;
if(pos < matchStart)
tokens.push(code.substring(pos, matchStart));
tokens.push(match);
}
if(pos < code.length)
tokens.push(code.substring(pos));
return tokens;
}
function parse(tokens, callback) {
for(var i = 0; i < tokens.length; ++i) {
var j = callback(tokens[i], tokens, i);
if(j === false) break;
else if(typeof j === 'number') i = j;
}
}
function skip(tokens, idx, limiter, escapes) {
while(++idx < tokens.length && tokens[idx] !== limiter)
if(escapes && tokens[idx] === '\\') ++idx;
return idx;
}
function removeDeclaration(token, tokens, idx) {
switch(token) {
case '/*':
return skip(tokens, idx, '*/');
case '//':
return skip(tokens, idx, '\n');
case ')':
tokens.splice(0, idx + 1);
return false;
}
}
function extractTopLevelFunctionNames(token, tokens, idx) {
switch(token) {
case '{':
++level;
return;
case '}':
--level;
return;
case '/*':
return skip(tokens, idx, '*/');
case '//':
return skip(tokens, idx, '\n');
case '"':
case '\'':
return skip(tokens, idx, token, true);
case 'function':
if(level === 1) {
while(++idx < tokens.length) {
token = tokens[idx];
if(token === '(')
return idx;
if(/^\s+$/.test(token))
continue;
if(token === '/*') {
idx = skip(tokens, idx, '*/');
continue;
}
if(token === '//') {
idx = skip(tokens, idx, '\n');
continue;
}
names.push(token);
return idx;
}
}
return;
}
}
function getTopLevelFunctionRefs(func) {
var tokens = tokenize(func.toString());
parse(tokens, removeDeclaration);
names = [], level = 0;
parse(tokens, extractTopLevelFunctionNames);
var code = tokens.join('') + '\nthis._refs = [' +
names.join(',') + '];';
return (new (new Function(code)))._refs;
}
return getTopLevelFunctionRefs;
})();
function testSuite() {
function testA() {
function testNested() {
}
}
// function testComment() {}
// function testGlobalFn() {}
function // comments
testB /* don't matter */
() // neither does whitespace
{
var s = "function testString() {}";
}
}
document.writeln(extractFunctions(testSuite).join('\n---\n'));
</script></pre>
Not as elegant as LISP-macros, but still nice what JAvaScript is capable of ;)
<pre>
<script type="text/javascript">
function someFn() {
/**
* Some comment
*/
function fn1() {
alert("/*This is not a comment, it's a string literal*/");
}
function // keyword
fn2 // name
(x, y) // arguments
{
/*
body
*/
}
function fn3() {
alert("this is the word function in a string literal");
}
var f = function () { // anonymous, ignore
};
}
var s = someFn.toString();
// remove inline comments
s = s.replace(/\/\/.*/g, "");
// compact all whitespace to a single space
s = s.replace(/\s{2,}/g, " ");
// remove all block comments, including those in string literals
s = s.replace(/\/\*.*?\*\//g, "");
document.writeln(s);
// remove string literals to avoid false matches with the keyword 'function'
s = s.replace(/'.*?'/g, "");
s = s.replace(/".*?"/g, "");
document.writeln(s);
// find all the function definitions
var matches = s.match(/function(.*?)\(/g);
for (var ii = 1; ii < matches.length; ++ii) {
// extract the function name
var funcName = matches[ii].replace(/function(.+)\(/, "$1");
// remove any remaining leading or trailing whitespace
funcName = funcName.replace(/\s+$|^\s+/g, "");
if (funcName === '') {
// anonymous function, discard
continue;
}
// output the results
document.writeln('[' + funcName + ']');
}
</script>
</pre>
I'm sure I missed something, but from your requirements in the original question, I think I've met the goal, including getting rid of the possibility of finding the function keyword in string literals.
One last point, I don't see any problem with mangling the string literals in the function blocks. Your requirement was to find the function names, so I didn't bother trying to preserve the function content.