Currently it is not possible in confluence to have the headings of the document structure numbered automatically. I am aware that there are (paid) 3rd party plugins available.
How can I achieve continuous numbered headings?
TL;DR
Create a bookmark for the following javascript and click it in edit mode in confluence to renumber your headings.
javascript:(function()%7Bfunction%20addIndex()%20%7Bvar%20indices%20%3D%20%5B%5D%3BjQuery(%22.ak-editor-content-area%20.ProseMirror%22).find(%22h1%2Ch2%2Ch3%2Ch4%2Ch5%2Ch6%22).each(function(i%2Ce)%20%7Bvar%20hIndex%20%3D%20parseInt(this.nodeName.substring(1))%20-%201%3Bif%20(indices.length%20-%201%20%3E%20hIndex)%20%7Bindices%3D%20indices.slice(0%2C%20hIndex%20%2B%201%20)%3B%7Dif%20(indices%5BhIndex%5D%20%3D%3D%20undefined)%20%7Bindices%5BhIndex%5D%20%3D%200%3B%7Dindices%5BhIndex%5D%2B%2B%3BjQuery(this).html(indices.join(%22.%22)%2B%22.%20%22%20%2B%20removeNo(jQuery(this).html()))%3B%7D)%3B%7Dfunction%20removeNo(str)%20%7Blet%20newstr%20%3D%20str.trim()%3Bnewstr%20%3D%20newstr.replace(%2F%5B%5Cu00A0%5Cu1680%E2%80%8B%5Cu180e%5Cu2000-%5Cu2009%5Cu200a%E2%80%8B%5Cu200b%E2%80%8B%5Cu202f%5Cu205f%E2%80%8B%5Cu3000%5D%2Fg%2C'%20')%3Bif(IsNumeric(newstr.substring(0%2Cnewstr.indexOf('%20'))))%7Breturn%20newstr.substring(newstr.indexOf('%20')%2B1).trim()%3B%7Dreturn%20newstr%3B%7Dfunction%20IsNumeric(num)%20%7Bnum%20%3D%20num.split('.').join(%22%22)%3Breturn%20(num%20%3E%3D0%20%7C%7C%20num%20%3C%200)%3B%7DaddIndex()%7D)()
Result
How to use
After changes to the structure have been made, clicking the bookmarked javascript renumbers the document.
Limitations are that it only provides n.n.n. numbering, but for many cases that's sufficient. The script can also be customized as required.
Background, explanation and disclosure
I tried this TaperMonkey script that apparently resulted from this post, but it didn't work as is. So I took its source code and stripped it of the integration code, old version compatibility and made some minor adjustments to get this:
function addIndex() {
var indices = [];
jQuery(".ak-editor-content-area .ProseMirror").find("h1,h2,h3,h4,h5,h6").each(function(i,e) {
var hIndex = parseInt(this.nodeName.substring(1)) - 1;
if (indices.length - 1 > hIndex) {
indices= indices.slice(0, hIndex + 1 );
}
if (indices[hIndex] == undefined) {
indices[hIndex] = 0;
}
indices[hIndex]++;
jQuery(this).html(indices.join(".")+". " + removeNo(jQuery(this).html()));
});
}
function removeNo(str) {
let newstr = str.trim();
newstr = newstr.replace(/[\u00A0\u1680\u180e\u2000-\u2009\u200a\u200b\u202f\u205f\u3000]/g,' ');
if(IsNumeric(newstr.substring(0,newstr.indexOf(' ')))){
return newstr.substring(newstr.indexOf(' ')+1).trim();
}
return newstr;
}
function IsNumeric(num) {
num = num.split('.').join("");
return (num >=0 || num < 0);
}
addIndex();
(I'm not a JavaScript developer, I'm sure it can be written nicer/better)
Then I used bookmarklet to convert it into the javascript bookmark at the top, which can be clicked to trigger the functionality.
Related
So, I never ever programmed JavaScript and never did anything with Google Script before either. I have a fairly good understanding of Visual Basic and macros in Excel and Word. Trying to make a fairly basic program: Plow through a list of variables in a spreadsheet, make a new sheet for each value, insert a formula in this new sheet, cell (1,1).
Debug accepts my program, no issues - however, nothing at all is happening when I run the program:
function kraft() {
var rightHere =
SpreadsheetApp.getActiveSpreadsheet().getActiveSheet().getRange("A1:A131");
var loopy;
var goshDarn = "";
for (loopy = 1; loopy < 132; loopy++) {
celly = rightHere.getCell(loopy,1);
vaerdi = celly.getValue();
fed = celly.getTextStyle();
console.log(vaerdi & " - " & fed);
if (vaerdi != "" && fed.isBold == false) {
SpreadsheetApp.getActiveSpreadsheet().insertSheet(vaerdi);
var thisOne = SpreadsheetApp.getActiveSpreadsheet().getSheetByName(vaerdi);
thisOne.deleteRows(500,500);
thisOne.deleteColumns(5, 23);
thisOne.getRange(1,1).setFormula("=ArrayFormula(FILTER('Individuelle varer'!A16:D30015,'Individuelle varer'!A16:A30015=" & Char(34) & vaerdi & Char(34) & ")))");
}
}
}
activeSheet could be called by name, so could activeSpreadsheet, I guess. But range A1:A131 has a ton of variables - some times there are empty lines and new headers (new headers are bold). But basically I want around 120 new sheets to appear in my spreadsheet, named like the lines here. But nothing happens. I tried to throw in a log thingy, but I cannot read those values anywhere.
I must be missing the most total basic thing of how to get script connected to a spreadsheet, I assume...
EDIT: I have tried to update code according to tips from here and other places, and it still does a wonderful nothing, but now looks like this:
function kraft() {
var rightHere = SpreadsheetApp.getActiveSpreadsheet().getActiveSheet().getRange("A1:A131");
var loopy;
var goshDarn = "";
for (loopy = 1; loopy < 132; loopy++) {
celly = rightHere.getCell(loopy,1);
vaerdi = celly.getValue();
fed = celly.getFontWeight();
console.log(vaerdi & " - " & fed);
if (vaerdi != "" && fed.isBold == false) {
SpreadsheetApp.getActiveSpreadsheet().insertSheet(vaerdi);
var thisOne = SpreadsheetApp.getActiveSpreadsheet().getSheetByName(vaerdi);
thisOne.deleteRows(500,500);
thisOne.deleteColumns(5, 23);
thisOne.getRange(1,1).setFormula("=ArrayFormula(FILTER('Individuelle varer'!A16:D30015,'Individuelle varer'!A16:A30015=" + "\"" + vaerdi + "\"" + ")))");
}
}
}
EDIT2: Thanks to exactly the advice I needed, the problem is now solved, with this code:
function kraft() {
var rightHere = SpreadsheetApp.getActiveSpreadsheet().getActiveSheet().getRange("A1:A131");
var loopy;
for (loopy = 1; loopy < 132; loopy++) {
celly = rightHere.getCell(loopy,1);
vaerdi = celly.getValue();
fed = celly.getFontWeight()
console.log(vaerdi & " - " & fed);
if (vaerdi != "" && fed != "bold") {
SpreadsheetApp.getActiveSpreadsheet().insertSheet(vaerdi);
var thisOne = SpreadsheetApp.getActiveSpreadsheet().getSheetByName(vaerdi);
thisOne.deleteRows(500,499);
thisOne.deleteColumns(5, 20);
thisOne.getRange(1,1).setFormula("=ArrayFormula(FILTER('Individuelle varer'!A16:D30015;'Individuelle varer'!A16:A30015=" + "\"" + vaerdi + "\"" + "))");
}
}
}
There are multiple issues with your script, but the main one is that you never actually call the isBold() function in your 'if' statement.
if (value && format.isBold() == false) {
//do something
}
Because you omitted the parentheses in 'fed.isBold', the expression never evaluates to 'true'. 'isBold' (without the parentheses) is of type Object as it's a function.
There are other issues that prevent the script from running properly:
Not using the 'var' keyword to declare variables and polluting the global scope. As a result, all variables you declare within your 'for' loop are not private to your function. Instead, they are attached to the global object and are accessible outside the function. https://prntscr.com/kjd8s5
Not using the built-in debugger. Running the function is not debugging. You should set the breakpoints and click the debug button to execute your function step-by-step and examine all values as it's being executed.
Deleting the non-existent columns. When you create the new sheet, you call the deleteColums(). There are 26 columns in total. The 1st parameter is the starting column while the 2nd one specifies how many columns must be deleted. Starting from column 5 and telling the script to remove 23 columns will throw an exception. Always refer to the documentation to avoid such errors.
console.log doesn't exist within the context of the Script Editor. You are NOT executing the scripts inside your browser, so Browser object model is not available. Use Logger.log(). Again, this is detailed in the documentation.
Your formula is not formatted properly.
JS is a dynamically typed language that's not easy to get used to. If you don't do at least some research prior to writing code, you'll be in for a lot of pain.
A online tool, such as JSCompress, will reduce code size up to 80%. It's easy to notice that the result, compressed code, removes space. Beyond the removal of EOL and ' ' characters, is there any other trickery needed to minify a js file?
Example compressed:
function glow(e){$("#"+e).fadeIn(700,function(){$(this).fadeOut(700)})}function startLevel(){ptrn=[],pos=0,setLevel(lvl),$("#mg-lvl").fadeOut("slow",function(){$("#mg-contain").prop("onclick",null).off("click"),$("#mg-contain").css("cursor","default"),$(this).text("Level "+lvl+": "+ptrn.length+" blink(s)."),$(this).fadeIn("slow"),showLevel(0)})}function setLevel(e){ptrn.push(Math.floor(3*Math.random()+1)),0==e||setLevel(--e)}function showLevel(e){$("#b"+ptrn[e]+"c").fadeOut(speed,function(){$("#ball_"+ptrn[e]).fadeOut(speed,function(){$("#b"+ptrn[e]+"c").fadeIn(speed),$(this).fadeIn(speed,function(){e+1<ptrn.length&&showLevel(++e,speed)})})}),e+1==ptrn.length&&setTimeout(bindKeys(1),ptrn.length*speed+15)}function bindKeys(e){for(var e=1;e<4;e++)bind(e)}function bind(e){$("#ball_"+e).on("click",function(){$("#b"+e+"c").fadeOut(speed,function(){$("#ball_"+e).fadeOut(speed,function(){$("#ball_"+e).fadeIn(speed),$("#b"+e+"c").fadeIn(speed),referee(e)&&unbind()})})})}function referee(e){if(pos<ptrn.length&&(e===ptrn[pos]?$("#mg-score").text(parseInt($("#mg-score").text())+1):end()),++pos==ptrn.length)return++lvl,speed-=40,!0}function unbind(){for(var e=1;e<4;e++)$("#ball_"+e).off();startLevel()}function nestedFade(e,n,t){e[n]&&$(e[n]).fadeOut("fast",function(){t[n]&&($(e),t[n]),nestedFade(e,++n,t)})}function end(){for(var e=[],n=[],t=1;t<4;t++)e.push("#b"+t+"c"),e.push("#ball_"+t),n.push(null);e.push("#mg-contain"),n.push('.fadeOut("slow")'),e.push("#mg-obj"),n.push(".fadeOut('slow')"),e.push("#bg-ball-container"),n.push(".toggle()"),nestedFade(e,0,n)}var ptrn=[],pos=0,lvl=1,speed=400,b1=setInterval(function(){glow("ball_1b",700)}),b2=setInterval(function(){glow("ball_2b",700)}),b3=setInterval(function(){glow("ball_3b",700)});
Example uncompressed:
var ptrn = [];
var pos = 0;
var lvl = 1;
var speed = 400;
/* make balls glow */
function glow(id)
{
$('#'+id).fadeIn(700, function(){$(this).fadeOut(700);})
}
var b1 = setInterval(function(){ glow('ball_1b',700) ,1500});
var b2 = setInterval(function(){ glow('ball_2b',700) ,1500});
var b3 = setInterval(function(){ glow('ball_3b',700) ,1500});
/* end */
function startLevel()
{
ptrn = [];
pos = 0;
/* set pattern for the level */
setLevel(lvl);
/* display prompt for level */
$('#mg-lvl').fadeOut("slow", function(){
$('#mg-contain').prop('onclick',null).off('click');
$('#mg-contain').css('cursor','default');
$(this).text("Level " + lvl + ": " + ptrn.length + " blink(s).");
$(this).fadeIn('slow');
/* play back the pattern for user to play */
showLevel(0); //TODO: use promise and deferred pattern to pull this out of fade function.
});
}
function setLevel(lvl)
{
ptrn.push(Math.floor((Math.random() * 3) + 1));
(lvl == 0 ) ? null : setLevel(--lvl);
}
function showLevel(i)
{
/* blink the balls */
$('#b'+ptrn[i]+'c').fadeOut(speed, function(){
$('#ball_'+ptrn[i]).fadeOut(speed, function(){
$('#b'+ptrn[i]+'c').fadeIn(speed);
$(this).fadeIn(speed, function(){
if(i+1<ptrn.length)
showLevel(++i,speed);
});
});
});
if( (i+1) == ptrn.length)
setTimeout( bindKeys(1), ptrn.length*speed+15) //after the pattern is revealed bind the clicker
}
function bindKeys(i)
{
for(var i=1;i<4;i++)
bind(i);
}
function bind(i)
{
$('#ball_'+i).on('click', function() {
$('#b'+i+'c').fadeOut(speed, function() {
$('#ball_'+i).fadeOut(speed, function() {
$('#ball_'+i).fadeIn(speed);
$('#b'+i+'c').fadeIn(speed);
if(referee(i))
unbind();
});
});
});
}
function referee(val)
{
if(pos < ptrn.length){
( val === ptrn[pos] ) ? $('#mg-score').text(parseInt($('#mg-score').text())+1) : end();
}
if(++pos == ptrn.length)
{
++lvl;
speed-=40;
return true;
}
}
function unbind()
{
for(var i=1;i<4;i++)
$( "#ball_"+i).off();
startLevel();
}
function nestedFade(id,i,func)
{
(!id[i]) ? 0 : $(id[i]).fadeOut('fast',function(){ if(func[i])
{$(id)+func[i];};nestedFade(id,++i,func);})
}
function end()
{
var id = [];
var func = [];
for(var i=1;i<4;i++){
id.push('#b'+i+'c');
id.push('#ball_'+i);
func.push(null)
}
id.push('#mg-contain');
func.push('.fadeOut("slow")');
id.push('#mg-obj');
func.push(".fadeOut('slow')");
id.push('#bg-ball-container');
func.push(".toggle()");
nestedFade(id,0,func);
}
Saves 32% on file size...and if that is the case, is it a fair assumption then that writing less is doing more for the end user?
The same way you can 'minify' a file to reduce its size, you can also 'uglify' a file, which takes your code and shortens things like variable names to the same end: reduce file size by reducing the number of characters in it (not just removing line breaks and space characters).
While it will reduce loadtime for a user, it's not a great practice to write minified/uglified-style code off the bat. That's why in almost any professional build/deploy process, you take your clear, descriptive code and then run your build processes to reduce the size of your files and eventually deploy versions that your end user will have a quicker time loading. You can always write your regular code, then run a compression process like the one you described, save it into a "public" folder and upload that for users to have access to, rather than your fleshed out code.
All a minifier will do is remove white space, which like you said, is ' ' and EOL characters. I believe you may be thinking of file compression tools such as a .zip file with the way your question is worded. Such file types (.zip) will find common strings in your file, and put references to the original string rather than having it written out 10 times. Meaning if the string "I like cake" shows up 4 times in your file, it will have "I like cake" in one location, and the other three locations will reference that first location, shortening the length of the file and therefore decreasing its size.
Well the main reason JS, CSS and HTML get's minified is to decrease the size of the files transmitted from server to client when a client requests a webpage. This decrease in size will allow for a faster load time. So technically writing less is more for a webpages load time, but realistically the effect of you as a developer consciously writing shorter code to minimize file size will either a.) Be to minimal a change to actually make a difference or b.) lead to loss of functionality or bugs due to the focus being on cutting down code length, not code quality.
I've written an extension for firefox which highlights all words on a web page (excluding some words in a given list).
What i've noticed is that (besides that my extension is terribly slow) some web pages get "destroyed", more specifically the layout gets destroyed (particularly websites with overlay advertising or fancy drop-down menus).
My code wraps <span> tags around every "word", or to be precise around every token, because i'm splitting the text nodes with a whitespace as seperator.
So is it possible anyway to realize this task without destroying the page's layout?
I'm iterating over all text nodes, split them, and iterate over every token.
When the token is in my list, i don't highlight it, else i wrap the <span> tag around it.
So any suggestions how this could be done faster would be helpful, too.
Here are some screenshots for a correctly highlighted and a not correctly highlighted web page:
right:
en.wikipedia.org before highlighting,
en.wikipedia.org after highlighting.
wrong:
developer.mozilla.org before highlighting,
developer.mozilla.org after highlighting.
OK. Study this code. It searches for all instances of "is" and highlights if it is not surrounded by word characters. Put this in your scratchpad while this tab is focused. You will see that words like "List" and other words containing "Is" are no highlighted, but all the "Is"'s are.
I basically made an addon here for you. You can now release this as an addon called RegEx FindBar and take all the credit....
var doc = gBrowser.contentDocument;
var ctrler = _getSelectionController(doc.defaultView);
var searchRange = doc.createRange();
searchRange.selectNodeContents(doc.documentElement);
let startPt = searchRange.cloneRange();
startPt.collapse(true);
let endPt = searchRange.cloneRange();
endPt.collapse(false);
let retRane = null;
let finder = Cc["#mozilla.org/embedcomp/rangefind;1"].createInstance().QueryInterface(Ci.nsIFind);
finder.caseSensitive = false;
var i = 0;
while (retRange = finder.Find('is', searchRange, startPt, endPt)) {
i++;
var stCont = retRange.startContainer;
var endCont = retRange.endContainer;
console.log('retRange(' + i + ') = ', retRange);
console.log('var txt = retRange.commonAncestorContainer.data',retRange.commonAncestorContainer.data);
//now test if one posiion before startOffset and one position after endOffset are WORD characters
var isOneCharBeforeStCharWordChar; //var that holds if the character before the start character is a word character
if (retRange.startOffset == 0) {
//no characters befor this characte so obviously not a word char
isOneCharBeforeStCharWordChar = false;
} else {
var oneCharBeforeStChar = stCont.data.substr(retRange.startOffset-1,1);
if (/\w/.test(oneCharBeforeStChar)) {
isOneCharBeforeStCharWordChar = true;
} else {
isOneCharBeforeStCharWordChar = false;
}
console.log('oneCharBeforeStChar',oneCharBeforeStChar);
}
var isOneCharAfterEndCharWordChar; //var that holds if the character before the start character is a word character
if (retRange.endOffset == endCont.length - 1) {
//no characters after this characte so obviously not a word char
isOneCharAfterEndCharWordChar = false;
} else {
var oneCharAferEndChar = endCont.data.substr(retRange.endOffset,1); //no need to subtract 1 from endOffset, it takes into account substr 2nd arg is length and is treated like length I THINK
if (/\w/.test(oneCharAferEndChar)) {
isOneCharAfterEndCharWordChar = true;
} else {
isOneCharAfterEndCharWordChar = false;
}
console.log('oneCharAferEndChar',oneCharAferEndChar);
}
if (isOneCharBeforeStCharWordChar == false && isOneCharAfterEndCharWordChar == false) {
//highlight it as surrounding characters are no word characters
_highlightRange(retRange, ctrler);
console.log('highlighted it as it was not surrounded by word charactes');
} else {
console.log('NOT hilte it as it was not surrounded by word charactes');
}
//break;
startPt = retRange.cloneRange();
startPt.collapse(false);
}
/*********************/
function _getEditableNode(aNode) {
while (aNode) {
if (aNode instanceof Ci.nsIDOMNSEditableElement)
return aNode.editor ? aNode : null;
aNode = aNode.parentNode;
}
return null;
}
function _highlightRange(aRange, aController) {
let node = aRange.startContainer;
let controller = aController;
let editableNode = this._getEditableNode(node);
if (editableNode)
controller = editableNode.editor.selectionController;
let findSelection = controller.getSelection(Ci.nsISelectionController.SELECTION_FIND);
findSelection.addRange(aRange);
if (editableNode) {
// Highlighting added, so cache this editor, and hook up listeners
// to ensure we deal properly with edits within the highlighting
if (!this._editors) {
this._editors = [];
this._stateListeners = [];
}
let existingIndex = this._editors.indexOf(editableNode.editor);
if (existingIndex == -1) {
let x = this._editors.length;
this._editors[x] = editableNode.editor;
this._stateListeners[x] = this._createStateListener();
this._editors[x].addEditActionListener(this);
this._editors[x].addDocumentStateListener(this._stateListeners[x]);
}
}
}
function _getSelectionController(aWindow) {
// display: none iframes don't have a selection controller, see bug 493658
if (!aWindow.innerWidth || !aWindow.innerHeight)
return null;
// Yuck. See bug 138068.
let docShell = aWindow.QueryInterface(Ci.nsIInterfaceRequestor)
.getInterface(Ci.nsIWebNavigation)
.QueryInterface(Ci.nsIDocShell);
let controller = docShell.QueryInterface(Ci.nsIInterfaceRequestor)
.getInterface(Ci.nsISelectionDisplay)
.QueryInterface(Ci.nsISelectionController);
return controller;
}
Oh edit my solution out, will update with proper solution, I see you want to highlight all words
This is the code how firefox highlights stuff without changing document: Finder.jsm - _highlight function. You will have to copy this and use it for the whole document, if you need help let me know and I'll do it.
Here was my solution to highlight all matches of single word: https://stackoverflow.com/a/22206366/1828637
Here man this is how you are going to highlight the whole document, I didn't finish the snippet but this is the start of it: Gist - HighlightTextInDocument
Here's the copy paste answer to highlight everything in the document. As you learn more about it share with us, like how you can highlight with a different color, right now its all pink O_O
function _getEditableNode(aNode) {
while (aNode) {
if (aNode instanceof Ci.nsIDOMNSEditableElement)
return aNode.editor ? aNode : null;
aNode = aNode.parentNode;
}
return null;
}
function _highlightRange(aRange, aController) {
let node = aRange.startContainer;
let controller = aController;
let editableNode = this._getEditableNode(node);
if (editableNode)
controller = editableNode.editor.selectionController;
let findSelection = controller.getSelection(Ci.nsISelectionController.SELECTION_FIND);
findSelection.addRange(aRange);
if (editableNode) {
// Highlighting added, so cache this editor, and hook up listeners
// to ensure we deal properly with edits within the highlighting
if (!this._editors) {
this._editors = [];
this._stateListeners = [];
}
let existingIndex = this._editors.indexOf(editableNode.editor);
if (existingIndex == -1) {
let x = this._editors.length;
this._editors[x] = editableNode.editor;
this._stateListeners[x] = this._createStateListener();
this._editors[x].addEditActionListener(this);
this._editors[x].addDocumentStateListener(this._stateListeners[x]);
}
}
}
function _getSelectionController(aWindow) {
// display: none iframes don't have a selection controller, see bug 493658
if (!aWindow.innerWidth || !aWindow.innerHeight)
return null;
// Yuck. See bug 138068.
let docShell = aWindow.QueryInterface(Ci.nsIInterfaceRequestor)
.getInterface(Ci.nsIWebNavigation)
.QueryInterface(Ci.nsIDocShell);
let controller = docShell.QueryInterface(Ci.nsIInterfaceRequestor)
.getInterface(Ci.nsISelectionDisplay)
.QueryInterface(Ci.nsISelectionController);
return controller;
}
var doc = gBrowser.contentDocument;
var searchRange = doc.createRange();
searchRange.selectNodeContents(doc.documentElement);
_highlightRange(searchRange,_getSelectionController(gBrowser.contentWindow))
#jervis, I can't make a comment on your comment under #Noitidart code as I don't have 50rep yet. So I have to post here.
Re:
I did it with 'gFindBar._highlightDoc(true, word)' now. I'm using firefox 17, so i dont know if gFindBar is state of the art. – jervis 40 mins ago
But I tested his code and and it works.
Don't use gFindBar.
Copy it and then paste it into your Scratchpad.
Why are you using gFindBar._highlightDoc(true, word) ? I thoght you wanted to highlight everything in the document? Where did you get _highlightDoc from? I don't see that anywhere in #Noitidart's code.
Regading yoru comment on iterate all words and use gFindBar._highlightDoc:
I did it with 'gFindBar._highlightDoc(true, word)' now. I'm using firefox 17, so i dont know if gFindBar is state of the art. – jervis 39 mins ago
Dude why do that.... I saw #Noitidart posted a per word solution on the linked topic: gBrowser.tabContainer.childNodes[0].linkedBrowser.finder.highlight(true, 'YOUR_WORD_HERE'); that is extremely easy, one line and no need to create text nodes spans or anything. You have to run this code on each tab you want to highlight in.
Recently, I've been attempting to emulate a small language in jQuery and JavaScript, yet I've come across what I believe is an issue. I think that I may be parsing everything completely wrong.
In the code:
#name Testing
#inputs
#outputs
#persist
#trigger
print("Test")
The current way I am separating and parsing the string is by splitting all of the code into lines, and then reading through this lines array using searches and splits. For example, I would find the name using something like:
if(typeof lines[line] === 'undefined')
{
}
else
{
if(lines[line].search('#name') == 0)
{
name = lines[line].split(' ')[1];
}
}
But I think that I may be largely wrong on how I am handling parsing.
While reading through examples on how other people are handling parsing of code blocks like this, it appeared that people parsed the entire block, instead of splitting it into lines as I do. I suppose the question of the matter is, what is the proper and conventional way of parsing things like this, and how do you suggest I use it to parse something such as this?
In simple cases like this regular expressions is your tool of choice:
matches = code.match(/#name\s+(\w+)/)
name = matches[1]
To parse "real" programming languages regexps are not powerful enough, you'll need a parser, either hand-written or automatically generated with a tool like PEG.
A general approach to parsing, that I like to take often is the following:
loop through the complete block of text, character by character.
if you find a character that signalizes the start of one unit, call a specialized subfunction to parse the next characters.
within each subfunction, call additional subfunctions if you find certain characters
return from every subfunction when a character is found, that signalizes, that the unit has ended.
Here is a small example:
var text = "#func(arg1,arg2)"
function parse(text) {
var i, max_i, ch, funcRes;
for (i = 0, max_i = text.length; i < max_i; i++) {
ch = text.charAt(i);
if (ch === "#") {
funcRes = parseFunction(text, i + 1);
i = funcRes.index;
}
}
console.log(funcRes);
}
function parseFunction(text, i) {
var max_i, ch, name, argsRes;
name = [];
for (max_i = text.length; i < max_i; i++) {
ch = text.charAt(i);
if (ch === "(") {
argsRes = parseArguments(text, i + 1);
return {
name: name.join(""),
args: argsRes.arr,
index: argsRes.index
};
}
name.push(ch);
}
}
function parseArguments(text, i) {
var max_i, ch, args, arg;
arg = [];
args = [];
for (max_i = text.length; i < max_i; i++) {
ch = text.charAt(i);
if (ch === ",") {
args.push(arg.join(""));
arg = [];
continue;
} else if (ch === ")") {
args.push(arg.join(""));
return {
arr: args,
index: i
};
}
arg.push(ch);
}
}
FIDDLE
this example just parses function expressions, that follow the syntax "#functionName(argumentName1, argumentName2, ...)". The general idea is to visit every character exactly once without the need to save current states like "hasSeenAtCharacter" or "hasSeenOpeningParentheses", which can get pretty messy when you parse large structures.
Please note that this is a very simplified example and it misses all the error handling and stuff like that, but I hope the general idea can be seen. Note also that I'm not saying that you should use this approach all the time. It's a very general approach, that can be used in many scenerios. But that doesn't mean that it can't be combined with regular expressions for instance, if it, at some part of your text, makes more sense than parsing each individual character.
And one last remark: you can save yourself the trouble if you put the specialized parsing function inside the main parsing function, so that all functions have access to the same variable i.
I'm programming my own autocomplete textbox control using C# and javascript on clientside. On client side i want to replace the characters in string which matching the characters the user was searching for to highlight it. For example if the user was searching for the characters 'bue' i want to replace this letters in the word 'marbuel' like so:
mar<span style="color:#81BEF7;font-weight:bold">bue</span>l
in order to give the matching part another color. This works pretty fine if i have 100-200 items in my autocomplete, but when it comes to 500 or more, it takes too mutch time.
The following code shows my method which does the logic for this:
HighlightTextPart: function (text, part) {
var currentPartIndex = 0;
var partLength = part.length;
var finalString = '';
var highlightPart = '';
var bFoundPart = false;
var bFoundPartHandled = false;
var charToAdd;
for (var i = 0; i < text.length; i++) {
var myChar = text[i];
charToAdd = null;
if (!bFoundPart) {
var myCharLower = myChar.toLowerCase();
var charToCompare = part[currentPartIndex].toLowerCase();
if (charToCompare == myCharLower) {
highlightPart += myChar;
if (currentPartIndex == partLength - 1)
bFoundPart = true;
currentPartIndex++;
}
else {
currentPartIndex = 0;
highlightPart = '';
charToAdd = myChar;
}
}
else
charToAdd = myChar;
if (bFoundPart && !bFoundPartHandled) {
finalString += '<span style="color:#81BEF7;font-weight:bold">' + highlightPart + '</span>';
bFoundPartHandled = true;
}
if (charToAdd != null)
finalString += charToAdd;
}
return finalString;
},
This method only highlight the first occurence of the matching part.
I use it as follows. Once the request is coming back from server i build an html UL list with the matching items by looping over each item and in each loop i call this method in order to highlight the matching part.
As i told for up to 100 items it woks pretty nice but it is too mutch for 500 or more.
Is there any way to make it faster? Maybe by using regex or some other technique?
I also thought about using "setTimeOut" to do it in a extra function or maybe do it only for the items, which currently are visible, because only a couple of items are visible while for the others you have to scroll.
Try limiting visible list size, so you are only showing 100 items at maximum for example. From a usability standpoint, perhaps even go down to only 20 items, so it would be even faster than that. Also consider using classes - see if it improves performance. So instead of
mar<span style="color:#81BEF7;font-weight:bold">bue</span>l
You will have this:
mar<span class="highlight">bue</span>l
String replacement in JavaScript is pretty easy with String.replace():
function linkify(s, part)
{
return s.replace(part, function(m) {
return '<span style="color:#81BEF7;font-weight:bold">' + htmlspecialchars(m) + '</span>';
});
}
function htmlspecialchars(txt)
{
return txt.replace('<', '<')
.replace('>', '>')
.replace('"', '"')
.replace('&', '&');
}
console.log(linkify('marbuel', 'bue'));
I fixed this problem by using regex instead of my method posted previous. I replace the string now with the following code:
return text.replace(new RegExp('(' + part + ')', 'gi'), "<span>$1</span>");
This is pretty fast. Much faster as the code above. 500 items in the autocomplete seems to be no problem. But can anybody explain, why this is so mutch faster as my method or doing it with string.replace without regex? I have no idea.
Thx!