Can I do the following?
function contains(element) {
// if the element is a Vertex object, do this
if (element instanceof Vertex) {
var vertex = element;
for ( var index in self.verticies) {
if (self.verticies[index].id == vertex.id) {
return true;
}
}
return false;
}
// else if the element is an Edge object, do this
else if (element instanceof Edge) {
var edge = element;
for ( var index in self.verticies) {
if (self.verticies[index].id == edge.id) {
return true;
}
}
return false;
} else {
// shouldn't come here
return false;
}
};
Basically... I want to be able to call contains() and pass it either a Vertex object or an Edge object but I don't want to have duplicate code. Is this the right way to do it? Furthermore, am I handling the assignment var vertex = element / var edge = element correctly? I want to assign element to another Vertex/Edge object and use that for my look up.
Let me know if I need to clarify.
Thanks,
Hristo
Your code should work fine.
Note, however, that there is no point (other than clarity, which is a good thing) in writing var edge = element.
Javascript variables are untyped; there is no difference between edge and element.
Also, you should probably throw an exception instead of
// shouldn't come here
return false;
Finally, why are you searching self.verticies for an Edge?
Note, by the way, that you still have duplicate code.
You can rewrite your function like this:
function contains(element) {
var searchSet;
// if the element is a Vertex object, do this
if (element instanceof Vertex)
searchSet = self.verticies;
else if (element instanceof Edge)
searchSet = self.edges;
else
throw Error("Unexpected argument");
for (var i = 0; i < searchSet.length; i++) {
if (searchSet[i].id == element.id)
return true;
}
return false;
}
Here's an approach that has a couple of advantages:
Smaller functions (no big if/else if chain)
Produces an appropriate error for missing functions without any additional coding
See what you think:
function contains(element) {
window['contains_' + typeof element](element);
};
contains_string = function(element) {
alert('string: ' + element);
};
contains('hi!'); // produces alert
contains(3); // error: 'undefined is not a function'
It has some downsides too.
The error message isn't terribly informative (not much worse than default behavior though)
You 'pollute' the 'window' object here a little (it'd work better as part of an object)
etc
Related
Using edge animate, I don't seem to have the control over orders of operations that I am looking for. I have a function that operates a switch and another that tests the conditions of one or many switches. The problem I am running into is edge keeps wanting to run the test before the switch.
I can have the switch launch the test but run into the issue that I load the objects in an array inside of edge. What I am thinking is I need a way of pre-loading variables that the function can use but they don't need to be global since they are only used in this one function.
Here is what I have so far.
Inside Edge Animate:
twoPhaseSwitch('.btn1','on'); //sets up switch 1
twoPhaseSwitch('.swtch1','off'); //sets up switch 2
conditionsArray(['.btn1','.swtch1']); // tells the test script what the buttons are
In JavaScript file:
function twoPhaseSwitch(object,state)
{
var obj = $(object);
stage.getSymbol(obj).stop(state);
obj.data('state',state);
obj.mousedown(function(e)
{
if(obj.state == 'off')
{
stage.getSymbol(obj).stop('on');
obj.state = 'on';
obj.data('state','on');
}else{
stage.getSymbol(obj).stop('off');
obj.state = 'off';
obj.data('state','off');
};
});
};
function conditionsArray(obj)
{
var answers = ['on','on'];
// compare lengths
if (obj.length != answers.length)
return 'Argument Miscount';
var challengResults = challangeArray();
if (challengResults == true)
{
lightOn('.LED1','on');
}else if(challengResults == false)
{
lightOn('.LED1','off');
};
console.log(challengResults);
function challangeArray()
{
for (var i = 0, l=obj.length; i < l; i++)
{
if ($(obj[i]).data('state') != answers[i]) {
return false;
}
}
return true;
};
};
function lightOn(lightOBJ,state)
{
lightOBJ = $(lightOBJ);
stage.getSymbol(lightOBJ).stop(state);
};
I use mousedown and mouseup currently to fake the order of operations but it brings some pretty unacceptable issues so I am trying to do this right.
did you try wrapping your code in
$( document ).ready(){
your code here
}
to prevent any javascript from running until the page loads?
So, I have this little code in my js file:
window.onload = function Equal() {
var a = 'b1'
var b = 'box1'
var bookstorname = localStorage.getItem(a)
if (bookstorname == 1) {
document.getElementById(b).setAttribute('checked','checked');
}
if (bookstorname == 0) {
document.getElementById(b).removeAttribute('checked','checked');
}
var a = 'b2'
var b = 'box2'
var bookstorname = localStorage.getItem(a)
if (bookstorname == 1) {
document.getElementById(b).setAttribute('checked','checked');
}
if (bookstorname == 0) {
document.getElementById(b).removeAttribute('checked','checked');
}
}
The function itself is not important (it equals checkboxvalues set in the localstorage), but I execute it 2 times. First time with var a & b set to 'b1' & 'box1'. Then I run the script again (same script), but with var a & b set to 'b2' & 'box2'. Now, this code works, but my question is if there is a shorter way to write this? I can imagine some sort of array with a loop, but I could not get it to work for some reason. The 2 variables are pairs, and I know this might be a dumb question, but I can't find the answer anywhere.
You can use a second function which will accept the local storage key and the checkbox id like
window.onload = function Equal() {
setCheckboxState('box1', 'b1');
setCheckboxState('box2', 'b2');
}
function setCheckboxState(id, key) {
document.getElementById(id).checked = 1 == localStorage.getItem(key);
}
You might separate common logic into another function
window.onload = function Equal() {
function extractFromStorage(a, b) {
var bookstorname = localStorage.getItem(a)
if (bookstorname == 1) {
document.getElementById(b).setAttribute('checked','checked');
}
if (bookstorname == 0) {
document.getElementById(b).removeAttribute('checked','checked');
}
}
extractFromStorage('b1', 'box1');
extractFromStorage('b2', 'box2');
}
function doTheStuff(a, b) {
var bookstorname = localStorage.getItem(a)
if (bookstorname == 1) {
document.getElementById(b).setAttribute('checked','checked');
}
if (bookstorname == 0) {
document.getElementById(b).removeAttribute('checked','checked');
}
}
window.onload = function Equal() {
doTheStuff('b1', 'box1');
doTheStuff('b2', 'box2');
}
?
This is how I would do it.
There are several problems with your code.
You do not check that the element you are stetting an attribute to
exists. You do not check if the localStorage item you get is
defined.
You pollute the global name space with the function name Equal.
That function should not be named with a capital as it is not a Object generator.
There is no need to use setAttribute and removeAttribute, in
fact removeAttribute makes no sense in this case as you can not
remove the checked attribute from the element. BTW why use setAttribute here and not for window.onload?
The checked attribute is either true or false, it does not use the
string "checked"
Binding the load event via the onload attribute is not safe as you may
block 3rd party code, or worse 3rd party code may block you.
There is no error checking. DOM pages are dynamic environments, pages
have adverts and content from many places that can interfer with your
code. Always code with this in mind. Check for possible errors and deal with them in a friendly way for the end user. In this case I used an alert, not friendly for a normal user but for you the coder.
My solution.
// add an event listener rather than replace the event listener
window.addEventListener(
"load", // for the load event
function(){
// the update function that is called for each item;
var update = function(item){
// the right hand side equates to true if the localstorage
// is equal to "1". LocalStorage allways returns a string or
// undefined if the key is not defined.
item.element.checked = localStorage[item.storageName] === "1";
}
// safe element getter
var getElement = function(eId){
var e = document.getElementById(eId); // try and get the element
if(e === null){ // does it exist?
throw "Missing element:"+eId; // no then we can not continue
// the program stops here unless
// you catch the error and deal with
// it gracefully.
}
return e; //ok return the element.
}
// Item creator. This creates a new item.
// sName is the local storage name
// eId id the element ID
var item = function(sName, eId){
return {
storageName: sName, // set the loaclStorage name
element:getElement(eId); // get the element and check its safe
};
}
// make it all safe
try{
// create an array of items.
var items = [
item("b1","box1"),
item("b2","box2")
];
// for each item update the element status
items.forEach(update);
}catch(e){
alert("Could not update page?");
}
}
);
In javascript using an object parameter is my preferred way of working with functions. To check that a function has the required parameters I either (Solution 1) loop through all the object parameters properties and throw an error or (Solution 2) wait until a required property is needed and throw an error. Solution two seems efficient but I have to throws in multiple places in the function. Solution 1 seems pragmatic but should probably be a reusable piece of code. Is there another solution I should be looking at?
You can actually do this
var propsNeeded = ["prop1", "prop2", "blah", "blah", "blah"],
obj = {
prop1: "Hi"
}
function hasRequiredProperties(props, obj){
return Object.keys(obj).sort().join() == propsNeeded.sort().join();
}
console.log(hasRequiredProperties(propsNeeded, obj)); // false
You can check for single properties like
function hasProperty(propName, obj){
return obj.hasOwnProperty(propName);
}
For consistency I would create require method and use it always when some property is required.
var require = function (key, object) {
if (typeof object[key] === 'undefined') {
throw new Error('Required property ' + key + ' is undefined');
}
};
I would test if required property exists as soon as I'm certain that property is needed. Like this:
var example = function (args) {
require('alwaysRequired', args);
// some code here which uses property alwaysRequired
if (args.something) {
require('sometimesRequired', args);
// some code here which uses property sometimesRequired
}
};
Using #Amit's answer I'd probably add a method to Object itself:
Object.prototype.hasAllProperties = function(props, fire){
var result = Object.keys(this).sort().join() == propsNeeded.sort().join();
if (fire && !result){
throw new Error('Object does not define all properties');
}
return result;
}
and in your function:
function someFunction(myObject){
var objComplete = myObject.hasAllProperties(["prop1", "prop2", "prop3"], false);
}
Update:
After noticing the problem with #Amit's original answer, here's what I suggest:
Object.prototype.hasAllProperties = function(props, fire){
var result = true;
$(props).each(function(i, e){
if (!this.hasOwnProperty(e) ) {
result = false;
return false;
}
});
if (fire && !result){
throw new Error('Object does not define all properties');
}
return result;
}
This is just a general case of checking for presence of keys on a object, which can be done easily enough with
requiredParams.every(function(prop) { return prop in paramObj; })
It almost reads like natural language. "Taking the required parameters, is EVERY one of them IN the parameter object?".
Just wrap this in function checkParams(paramObj, requiredParams) for easy re-use.
More generally, this is the problem of asking if one list (in this case the list of required parameters) is included in another list (the keys on the params object). So we can write a general routine for list inclusion:
function listIncluded(list1, list2) {
return list1.every(function(e) { return list2.indexOf(e) !== -1; });
}
Then our parameter-checking becomes
function checkParams(paramObj, requiredParams) {
return listIncluded(requiredParams, Object.keys(paramObj));
}
If you want to know if object has at least some properties you can use this function without third parameter:
function hasRequiredProperties(propsNeeded, obj, strict) {
if (strict) return Object.keys(obj).sort().join() == propsNeeded.sort().join();
for (var i in propsNeeded ) {
if (!obj.hasOwnProperty(propsNeeded[i])) return false;
}
return true;
};
Example:
options = {url: {
protocol: 'https:',
hostname: 'encrypted.google.com',
port: '80'
}
};
propsNeeded = ['protocol', 'hostname'];
hasRequiredProperties(propsNeeded, options.url); // true
hasRequiredProperties(propsNeeded, options.url, true); // false
Maybe some of you know about AOP, in some languages using AOP can lead you to be able to inject code after, before, or while a method is executing,etc.
What I want is to apply the same in Javascript, I am currently working on a massive app which has more than 300 ajax calls, and every time I need to do some change on the catch statement on them, I have to modify them one by one which is very tedious.
What I want to do is something like :
functionName.before("try {")
functionName.after("} catch(ex){
//dostuff
}")
Is it possible? I know there are things like .call, or the arguments object inside every function..which seem pretty meta-function (AOP) functionalities.
Not with before and after, but a wrap will work:
Function.prototype.wrapTry = function(handle) {
var fn = this;
return function() {
try {
return fn.apply(this, arguments);
} catch(e) {
return handle(e);
}
};
};
Then use it like
var safeFunction = functionName.wrapTry(doStuff);
In JavaScript, functions are first-class objects. That means you can manipulate or redeclare them.
Assuming that there is a "foo" function:
var originalFoo = foo;
foo = function()
{
// "before" code.
// Call the original function.
originalFoo.apply(this, arguments);
// "after" code.
};
After that, any call to foo() will call the new function: even with parameters.
Old question but you may take a look over this https://github.com/k1r0s/kaop-ts/blob/master/docs/api.md#available-join-points
import { onException } from "kaop-ts"
import handlingException from "./somewhere"
class Something {
#onException(handlingException)
method() {
// stuff that may throw an error
}
}
I also will give a late answer in order to shed some light onto this special case that every then and now pops up as JavaScript and AOP.
Firstly, cases like the very one presented by the OP always ask for modifying already existing functionality, thus targeting closed code that sometimes is not even owned by the party that sees itself challenged from modifying the control flow of such code.
Why then, not just name it like that ... JavaScript method modification or JavaScript method modifiers.
Secondly, because of already riding the horse of terminology, altering closed functionality in JavaScript has nothing to do with Aspect-oriented Programming unless an implementation that claims to be AO provides abstraction and code-reuse levels for at least Aspect, Advice and Pointcut.
Last, for what the OP is going to achieve and what also has been the accepted answer, there does exist a a whole bunch of before, after around / wrap solutions, almost always unfortunately mentioning AO(P), and in far too many cases not taking care of the context or target which is essential to method modification.
The example I do provide uses a prototypal implementation of afterThrowing. Because JavaScript already features a standardized bind, I'm firmly convinced that Function.prototype is the right place as well for some other method-modifiers
like before, after, around, afterThrowing
and afterFinally.
// OP's example pseudo code
//
// functionName.before("try {")
//
// functionName.after("} catch(ex){
// dostuff
// }")
function doStuffAfterThrowing(exception, originalArguments) {
"use strict";
var context = this;
console.log('context : ', context);
console.log('String(exception) : ', String(exception));
console.log('originalArguments : ', originalArguments);
return "safely handled exception";
}
function doFail() {
throw (new ReferenceError);
}
function oneOutOfManyAjaxCallbacks(payload) {
doFail();
}
var jsonData = {
"foo": "foo",
"bar": "bar"
};
var someModifiedAjaxCallback = oneOutOfManyAjaxCallbacks.afterThrowing(doStuffAfterThrowing, { x: 'y' });
// does fail controlled/handled.
console.log('someModifiedAjaxCallback(jsonData) : ', someModifiedAjaxCallback(jsonData));
// does fail "Uncaught".
console.log('oneOutOfManyAjaxCallbacks(jsonData) : ', oneOutOfManyAjaxCallbacks(jsonData));
.as-console-wrapper { min-height: 100%!important; top: 0; }
<script>
(function (Function) {
var
isFunction = function (type) {
return (
(typeof type == "function")
&& (typeof type.call == "function")
&& (typeof type.apply == "function")
);
},
getSanitizedTarget = function (target) {
return ((target != null) && target) || null;
}
;
Function.prototype.afterThrowing = function (handler, target) { // afterThrowing
target = getSanitizedTarget(target);
var proceed = this ;
return (isFunction(handler) && isFunction(proceed) && function () {
var ret, args = arguments;
try {
ret = proceed.apply(target, args);
} catch (exc) {
ret = handler.call(target, exc, args);
//throw exc;
}
return ret;
}) || proceed;
};
}(Function));
</script>
Having come that far one might also consider reading ...
sandwich pattern in javascript code
Can you alter a Javascript function after declaring it?
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.