simply-beautiful
Version:
Beautify HTML, JS, CSS, and JSON in the browser or in Node.js!
1,435 lines (1,218 loc) • 74.8 kB
JavaScript
(function (root, factory) {
// https://github.com/umdjs/umd/blob/master/templates/returnExports.js
if (typeof define === 'function' && define.amd) {
// AMD. Register as an anonymous module.
define([], factory);
} else if (typeof module === 'object' && module.exports) {
// Node. Does not work with strict CommonJS, but
// only CommonJS-like environments that support module.exports,
// like Node.
module.exports = factory();
} else {
// Browser globals (root is window)
root.returnExports = factory();
}
}(typeof self !== 'undefined' ? self : this, function () {
var environment = (Object.prototype.toString.call(typeof process !== 'undefined' ? process : 0) === '[object process]') ? 'node' : 'browser';
/*
JS
Style HTML
---------------
Written by Nochum Sossonko, (nsossonko@hotmail.com)
Based on code initially developed by: Einar Lielmanis, <elfz@laacz.lv>
http://jsbeautifier.org/
You are free to use this in any way you want, in case you find this useful or working for you.
Usage:
style_html(html_source);
style_html(html_source, options);
The options are:
indent_size (default 4) — indentation size,
indent_char (default space) — character to indent with,
max_char (default 70) - maximum amount of characters per line,
brace_style (default "collapse") - "collapse" | "expand" | "end-expand"
put braces on the same line as control statements (default), or put braces on own line (Allman / ANSI style), or just put end braces on own line.
unformatted (defaults to inline tags) - list of tags, that shouldn't be reformatted
indent_scripts (default normal) - "keep"|"separate"|"normal"
e.g.
style_html(html_source, {
'indent_size': 2,
'indent_char': ' ',
'max_char': 78,
'brace_style': 'expand',
'unformatted': ['a', 'sub', 'sup', 'b', 'i', 'u']
});
*/
function style_html(html_source, options) {
//Wrapper function to invoke all the necessary constructors and deal with the output.
var multi_parser,
indent_size,
indent_character,
max_char,
brace_style,
unformatted;
options = options || {};
indent_size = options.indent_size || 4;
indent_character = options.indent_char || ' ';
brace_style = options.brace_style || 'collapse';
max_char = options.max_char == 0 ? Infinity : options.max_char || 70;
unformatted = options.unformatted || ['a', 'span', 'bdo', 'em', 'strong', 'dfn', 'code', 'samp', 'kbd', 'var', 'cite', 'abbr', 'acronym', 'q', 'sub', 'sup', 'tt', 'i', 'b', 'big', 'small', 'u', 's', 'strike', 'font', 'ins', 'del', 'pre', 'address', 'dt', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'];
function Parser() {
this.pos = 0; //Parser position
this.token = '';
this.current_mode = 'CONTENT'; //reflects the current Parser mode: TAG/CONTENT
this.tags = { //An object to hold tags, their position, and their parent-tags, initiated with default values
parent: 'parent1',
parentcount: 1,
parent1: ''
};
this.tag_type = '';
this.token_text = this.last_token = this.last_text = this.token_type = '';
this.Utils = { //Uilities made available to the various functions
whitespace: "\n\r\t ".split(''),
single_token: 'br,input,link,meta,!doctype,basefont,base,area,hr,wbr,param,img,isindex,?xml,embed,?php,?,?='.split(','), //all the single tags for HTML
extra_liners: 'head,body,/html'.split(','), //for tags that need a line of whitespace before them
in_array: function (what, arr) {
for (var i=0; i<arr.length; i++) {
if (what === arr[i]) {
return true;
}
}
return false;
}
}
this.get_content = function () { //function to capture regular content between tags
var input_char = '',
content = [],
space = false; //if a space is needed
while (this.input.charAt(this.pos) !== '<') {
if (this.pos >= this.input.length) {
return content.length?content.join(''):['', 'TK_EOF'];
}
input_char = this.input.charAt(this.pos);
this.pos++;
this.line_char_count++;
if (this.Utils.in_array(input_char, this.Utils.whitespace)) {
if (content.length) {
space = true;
}
this.line_char_count--;
continue; //don't want to insert unnecessary space
}
else if (space) {
if (this.line_char_count >= this.max_char) { //insert a line when the max_char is reached
content.push('\n');
for (var i=0; i<this.indent_level; i++) {
content.push(this.indent_string);
}
this.line_char_count = 0;
}
else{
content.push(' ');
this.line_char_count++;
}
space = false;
}
content.push(input_char); //letter at-a-time (or string) inserted to an array
}
return content.length?content.join(''):'';
}
this.get_contents_to = function (name) { //get the full content of a script or style to pass to js_beautify
if (this.pos == this.input.length) {
return ['', 'TK_EOF'];
}
var input_char = '';
var content = '';
var reg_match = new RegExp('\<\/' + name + '\\s*\>', 'igm');
reg_match.lastIndex = this.pos;
var reg_array = reg_match.exec(this.input);
var end_script = reg_array?reg_array.index:this.input.length; //absolute end of script
if(this.pos < end_script) { //get everything in between the script tags
content = this.input.substring(this.pos, end_script);
this.pos = end_script;
}
return content;
}
this.record_tag = function (tag){ //function to record a tag and its parent in this.tags Object
if (this.tags[tag + 'count']) { //check for the existence of this tag type
this.tags[tag + 'count']++;
this.tags[tag + this.tags[tag + 'count']] = this.indent_level; //and record the present indent level
}
else { //otherwise initialize this tag type
this.tags[tag + 'count'] = 1;
this.tags[tag + this.tags[tag + 'count']] = this.indent_level; //and record the present indent level
}
this.tags[tag + this.tags[tag + 'count'] + 'parent'] = this.tags.parent; //set the parent (i.e. in the case of a div this.tags.div1parent)
this.tags.parent = tag + this.tags[tag + 'count']; //and make this the current parent (i.e. in the case of a div 'div1')
}
this.retrieve_tag = function (tag) { //function to retrieve the opening tag to the corresponding closer
if (this.tags[tag + 'count']) { //if the openener is not in the Object we ignore it
var temp_parent = this.tags.parent; //check to see if it's a closable tag.
while (temp_parent) { //till we reach '' (the initial value);
if (tag + this.tags[tag + 'count'] === temp_parent) { //if this is it use it
break;
}
temp_parent = this.tags[temp_parent + 'parent']; //otherwise keep on climbing up the DOM Tree
}
if (temp_parent) { //if we caught something
this.indent_level = this.tags[tag + this.tags[tag + 'count']]; //set the indent_level accordingly
this.tags.parent = this.tags[temp_parent + 'parent']; //and set the current parent
}
delete this.tags[tag + this.tags[tag + 'count'] + 'parent']; //delete the closed tags parent reference...
delete this.tags[tag + this.tags[tag + 'count']]; //...and the tag itself
if (this.tags[tag + 'count'] == 1) {
delete this.tags[tag + 'count'];
}
else {
this.tags[tag + 'count']--;
}
}
}
this.get_tag = function () { //function to get a full tag and parse its type
var input_char = '',
content = [],
space = false,
tag_start, tag_end;
do {
if (this.pos >= this.input.length) {
return content.length?content.join(''):['', 'TK_EOF'];
}
input_char = this.input.charAt(this.pos);
this.pos++;
this.line_char_count++;
if (this.Utils.in_array(input_char, this.Utils.whitespace)) { //don't want to insert unnecessary space
space = true;
this.line_char_count--;
continue;
}
if (input_char === "'" || input_char === '"') {
if (!content[1] || content[1] !== '!') { //if we're in a comment strings don't get treated specially
input_char += this.get_unformatted(input_char);
space = true;
}
}
if (input_char === '=') { //no space before =
space = false;
}
if (content.length && content[content.length-1] !== '=' && input_char !== '>'
&& space) { //no space after = or before >
if (this.line_char_count >= this.max_char) {
this.print_newline(false, content);
this.line_char_count = 0;
}
else {
content.push(' ');
this.line_char_count++;
}
space = false;
}
if (input_char === '<') {
tag_start = this.pos - 1;
}
content.push(input_char); //inserts character at-a-time (or string)
} while (input_char !== '>');
var tag_complete = content.join('');
var tag_index;
if (tag_complete.indexOf(' ') != -1) { //if there's whitespace, thats where the tag name ends
tag_index = tag_complete.indexOf(' ');
}
else { //otherwise go with the tag ending
tag_index = tag_complete.indexOf('>');
}
var tag_check = tag_complete.substring(1, tag_index).toLowerCase();
if (tag_complete.charAt(tag_complete.length-2) === '/' ||
this.Utils.in_array(tag_check, this.Utils.single_token)) { //if this tag name is a single tag type (either in the list or has a closing /)
this.tag_type = 'SINGLE';
}
else if (tag_check === 'script') { //for later script handling
this.record_tag(tag_check);
this.tag_type = 'SCRIPT';
}
else if (tag_check === 'style') { //for future style handling (for now it justs uses get_content)
this.record_tag(tag_check);
this.tag_type = 'STYLE';
}
else if (this.Utils.in_array(tag_check, unformatted)) { // do not reformat the "unformatted" tags
var comment = this.get_unformatted('</'+tag_check+'>', tag_complete); //...delegate to get_unformatted function
content.push(comment);
// Preserve collapsed whitespace either before or after this tag.
if (tag_start > 0 && this.Utils.in_array(this.input.charAt(tag_start - 1), this.Utils.whitespace)){
content.splice(0, 0, this.input.charAt(tag_start - 1));
}
tag_end = this.pos - 1;
if (this.Utils.in_array(this.input.charAt(tag_end + 1), this.Utils.whitespace)){
content.push(this.input.charAt(tag_end + 1));
}
this.tag_type = 'SINGLE';
}
else if (tag_check.charAt(0) === '!') { //peek for <!-- comment
if (tag_check.indexOf('[if') != -1) { //peek for <!--[if conditional comment
if (tag_complete.indexOf('!IE') != -1) { //this type needs a closing --> so...
var comment = this.get_unformatted('-->', tag_complete); //...delegate to get_unformatted
content.push(comment);
}
this.tag_type = 'START';
}
else if (tag_check.indexOf('[endif') != -1) {//peek for <!--[endif end conditional comment
this.tag_type = 'END';
this.unindent();
}
else if (tag_check.indexOf('[cdata[') != -1) { //if it's a <[cdata[ comment...
var comment = this.get_unformatted(']]>', tag_complete); //...delegate to get_unformatted function
content.push(comment);
this.tag_type = 'SINGLE'; //<![CDATA[ comments are treated like single tags
}
else {
var comment = this.get_unformatted('-->', tag_complete);
content.push(comment);
this.tag_type = 'SINGLE';
}
}
else {
if (tag_check.charAt(0) === '/') { //this tag is a double tag so check for tag-ending
this.retrieve_tag(tag_check.substring(1)); //remove it and all ancestors
this.tag_type = 'END';
}
else { //otherwise it's a start-tag
this.record_tag(tag_check); //push it on the tag stack
this.tag_type = 'START';
}
if (this.Utils.in_array(tag_check, this.Utils.extra_liners)) { //check if this double needs an extra line
this.print_newline(true, this.output);
}
}
return content.join(''); //returns fully formatted tag
}
this.get_unformatted = function (delimiter, orig_tag) { //function to return unformatted content in its entirety
if (orig_tag && orig_tag.indexOf(delimiter) != -1) {
return '';
}
var input_char = '';
var content = '';
var space = true;
do {
if (this.pos >= this.input.length) {
return content;
}
input_char = this.input.charAt(this.pos);
this.pos++
if (this.Utils.in_array(input_char, this.Utils.whitespace)) {
if (!space) {
this.line_char_count--;
continue;
}
if (input_char === '\n' || input_char === '\r') {
content += '\n';
/* Don't change tab indention for unformatted blocks. If using code for html editing, this will greatly affect <pre> tags if they are specified in the 'unformatted array'
for (var i=0; i<this.indent_level; i++) {
content += this.indent_string;
}
space = false; //...and make sure other indentation is erased
*/
this.line_char_count = 0;
continue;
}
}
content += input_char;
this.line_char_count++;
space = true;
} while (content.indexOf(delimiter) == -1);
return content;
}
this.get_token = function () { //initial handler for token-retrieval
var token;
if (this.last_token === 'TK_TAG_SCRIPT' || this.last_token === 'TK_TAG_STYLE') { //check if we need to format javascript
var type = this.last_token.substr(7)
token = this.get_contents_to(type);
if (typeof token !== 'string') {
return token;
}
return [token, 'TK_' + type];
}
if (this.current_mode === 'CONTENT') {
token = this.get_content();
if (typeof token !== 'string') {
return token;
}
else {
return [token, 'TK_CONTENT'];
}
}
if (this.current_mode === 'TAG') {
token = this.get_tag();
if (typeof token !== 'string') {
return token;
}
else {
var tag_name_type = 'TK_TAG_' + this.tag_type;
return [token, tag_name_type];
}
}
}
this.get_full_indent = function (level) {
level = this.indent_level + level || 0;
if (level < 1)
return '';
return Array(level + 1).join(this.indent_string);
}
this.printer = function (js_source, indent_character, indent_size, max_char, brace_style) { //handles input/output and some other printing functions
this.input = js_source || ''; //gets the input for the Parser
this.output = [];
this.indent_character = indent_character;
this.indent_string = '';
this.indent_size = indent_size;
this.brace_style = brace_style;
this.indent_level = 0;
this.max_char = max_char;
this.line_char_count = 0; //count to see if max_char was exceeded
for (var i=0; i<this.indent_size; i++) {
this.indent_string += this.indent_character;
}
this.print_newline = function (ignore, arr) {
this.line_char_count = 0;
if (!arr || !arr.length) {
return;
}
if (!ignore) { //we might want the extra line
while (this.Utils.in_array(arr[arr.length-1], this.Utils.whitespace)) {
arr.pop();
}
}
arr.push('\n');
for (var i=0; i<this.indent_level; i++) {
arr.push(this.indent_string);
}
}
this.print_token = function (text) {
this.output.push(text);
}
this.indent = function () {
this.indent_level++;
}
this.unindent = function () {
if (this.indent_level > 0) {
this.indent_level--;
}
}
}
return this;
}
/*_____________________--------------------_____________________*/
multi_parser = new Parser(); //wrapping functions Parser
multi_parser.printer(html_source, indent_character, indent_size, max_char, brace_style); //initialize starting values
while (true) {
var t = multi_parser.get_token();
multi_parser.token_text = t[0];
multi_parser.token_type = t[1];
if (multi_parser.token_type === 'TK_EOF') {
break;
}
switch (multi_parser.token_type) {
case 'TK_TAG_START':
multi_parser.print_newline(false, multi_parser.output);
multi_parser.print_token(multi_parser.token_text);
multi_parser.indent();
multi_parser.current_mode = 'CONTENT';
break;
case 'TK_TAG_STYLE':
case 'TK_TAG_SCRIPT':
multi_parser.print_newline(false, multi_parser.output);
multi_parser.print_token(multi_parser.token_text);
multi_parser.current_mode = 'CONTENT';
break;
case 'TK_TAG_END':
//Print new line only if the tag has no content and has child
if (multi_parser.last_token === 'TK_CONTENT' && multi_parser.last_text === '') {
var tag_name = multi_parser.token_text.match(/\w+/)[0];
var tag_extracted_from_last_output = multi_parser.output[multi_parser.output.length -1].match(/<\s*(\w+)/);
if (tag_extracted_from_last_output === null || tag_extracted_from_last_output[1] !== tag_name)
multi_parser.print_newline(true, multi_parser.output);
}
multi_parser.print_token(multi_parser.token_text);
multi_parser.current_mode = 'CONTENT';
break;
case 'TK_TAG_SINGLE':
// Don't add a newline before elements that should remain unformatted.
var tag_check = multi_parser.token_text.match(/^\s*<([a-z]+)/i);
if (!tag_check || !multi_parser.Utils.in_array(tag_check[1], unformatted)){
multi_parser.print_newline(false, multi_parser.output);
}
multi_parser.print_token(multi_parser.token_text);
multi_parser.current_mode = 'CONTENT';
break;
case 'TK_CONTENT':
if (multi_parser.token_text !== '') {
multi_parser.print_token(multi_parser.token_text);
}
multi_parser.current_mode = 'TAG';
break;
case 'TK_STYLE':
case 'TK_SCRIPT':
if (multi_parser.token_text !== '') {
multi_parser.output.push('\n');
var text = multi_parser.token_text;
if (multi_parser.token_type == 'TK_SCRIPT') {
var _beautifier = typeof js_beautify == 'function' && js_beautify;
} else if (multi_parser.token_type == 'TK_STYLE') {
var _beautifier = typeof css_beautify == 'function' && css_beautify;
}
if (options.indent_scripts == "keep") {
var script_indent_level = 0;
} else if (options.indent_scripts == "separate") {
var script_indent_level = -multi_parser.indent_level;
} else {
var script_indent_level = 1;
}
var indentation = multi_parser.get_full_indent(script_indent_level);
if (_beautifier) {
// call the Beautifier if avaliable
text = _beautifier(text.replace(/^\s*/, indentation), options);
} else {
// simply indent the string otherwise
var white = text.match(/^\s*/)[0];
var _level = white.match(/[^\n\r]*$/)[0].split(multi_parser.indent_string).length - 1;
var reindent = multi_parser.get_full_indent(script_indent_level -_level);
text = text.replace(/^\s*/, indentation)
.replace(/\r\n|\r|\n/g, '\n' + reindent)
.replace(/\s*$/, '');
}
if (text) {
multi_parser.print_token(text);
multi_parser.print_newline(true, multi_parser.output);
}
}
multi_parser.current_mode = 'TAG';
break;
}
multi_parser.last_token = multi_parser.token_type;
multi_parser.last_text = multi_parser.token_text;
}
return multi_parser.output.join('');
}
/*
CSS Beautifier
---------------
Written by Harutyun Amirjanyan, (amirjanyan@gmail.com)
Based on code initially developed by: Einar Lielmanis, <elfz@laacz.lv>
http://jsbeautifier.org/
You are free to use this in any way you want, in case you find this useful or working for you.
Usage:
css_beautify(source_text);
css_beautify(source_text, options);
The options are:
indent_size (default 4) — indentation size,
indent_char (default space) — character to indent with,
e.g
css_beautify(css_source_text, {
'indent_size': 1,
'indent_char': '\t'
});
*/
// http://www.w3.org/TR/CSS21/syndata.html#tokenization
// http://www.w3.org/TR/css3-syntax/
function css_beautify(source_text, options) {
options = options || {};
var indentSize = options.indent_size || 4;
var indentCharacter = options.indent_char || ' ';
// compatibility
if (typeof indentSize == "string")
indentSize = parseInt(indentSize);
// tokenizer
var whiteRe = /^\s+$/;
var wordRe = /[\w$\-_]/;
var pos = -1, ch;
function next() {
return ch = source_text.charAt(++pos)
}
function peek() {
return source_text.charAt(pos+1)
}
function eatString(comma) {
var start = pos;
while(next()){
if (ch=="\\"){
next();
next();
} else if (ch == comma) {
break;
} else if (ch == "\n") {
break;
}
}
return source_text.substring(start, pos + 1);
}
function eatWhitespace() {
var start = pos;
while (whiteRe.test(peek()))
pos++;
return pos != start;
}
function skipWhitespace() {
var start = pos;
do{
}while (whiteRe.test(next()))
return pos != start + 1;
}
function eatComment() {
var start = pos;
next();
while (next()) {
if (ch == "*" && peek() == "/") {
pos ++;
break;
}
}
return source_text.substring(start, pos + 1);
}
function lookBack(str, index) {
return output.slice(-str.length + (index||0), index).join("").toLowerCase() == str;
}
// printer
var indentString = source_text.match(/^[\r\n]*[\t ]*/)[0];
var singleIndent = Array(indentSize + 1).join(indentCharacter);
var indentLevel = 0;
function indent() {
indentLevel++;
indentString += singleIndent;
}
function outdent() {
indentLevel--;
indentString = indentString.slice(0, -indentSize);
}
var print = {}
print["{"] = function(ch) {
print.singleSpace();
output.push(ch);
print.newLine();
}
print["}"] = function(ch) {
print.newLine();
output.push(ch);
print.newLine();
}
print.newLine = function(keepWhitespace) {
if (!keepWhitespace)
while (whiteRe.test(output[output.length - 1]))
output.pop();
if (output.length)
output.push('\n');
if (indentString)
output.push(indentString);
}
print.singleSpace = function() {
if (output.length && !whiteRe.test(output[output.length - 1]))
output.push(' ');
}
var output = [];
if (indentString)
output.push(indentString);
/*_____________________--------------------_____________________*/
while(true) {
var isAfterSpace = skipWhitespace();
if (!ch)
break;
if (ch == '{') {
indent();
print["{"](ch);
} else if (ch == '}') {
outdent();
print["}"](ch);
} else if (ch == '"' || ch == '\'') {
output.push(eatString(ch))
} else if (ch == ';') {
output.push(ch, '\n', indentString);
} else if (ch == '/' && peek() == '*') { // comment
print.newLine();
output.push(eatComment(), "\n", indentString);
} else if (ch == '(') { // may be a url
if (lookBack("url", -1)) {
output.push(ch);
eatWhitespace();
if (next()) {
if (ch != ')' && ch != '"' && ch != '\'')
output.push(eatString(')'));
else
pos--;
}
} else {
if (isAfterSpace)
print.singleSpace();
output.push(ch);
eatWhitespace();
}
} else if (ch == ')') {
output.push(ch);
} else if (ch == ',') {
eatWhitespace();
output.push(ch);
print.singleSpace();
} else if (ch == ']') {
output.push(ch);
} else if (ch == '[' || ch == '=') { // no whitespace before or after
eatWhitespace();
output.push(ch);
} else {
if (isAfterSpace)
print.singleSpace();
output.push(ch);
}
}
var sweetCode = output.join('').replace(/[\n ]+$/, '');
return sweetCode;
}
if (typeof exports !== "undefined")
exports.css_beautify = css_beautify;
/*jslint onevar: false, plusplus: false */
/*jshint curly:true, eqeqeq:true, laxbreak:true, noempty:false */
/*
JS Beautifier
---------------
Written by Einar Lielmanis, <einar@jsbeautifier.org>
http://jsbeautifier.org/
Originally converted to javascript by Vital, <vital76@gmail.com>
"End braces on own line" added by Chris J. Shull, <chrisjshull@gmail.com>
You are free to use this in any way you want, in case you find this useful or working for you.
Usage:
js_beautify(js_source_text);
js_beautify(js_source_text, options);
The options are:
indent_size (default 4) - indentation size,
indent_char (default space) - character to indent with,
preserve_newlines (default true) - whether existing line breaks should be preserved,
max_preserve_newlines (default unlimited) - maximum number of line breaks to be preserved in one chunk,
jslint_happy (default false) - if true, then jslint-stricter mode is enforced.
jslint_happy !jslint_happy
---------------------------------
function () function()
brace_style (default "collapse") - "collapse" | "expand" | "end-expand" | "expand-strict"
put braces on the same line as control statements (default), or put braces on own line (Allman / ANSI style), or just put end braces on own line.
expand-strict: put brace on own line even in such cases:
var a =
{
a: 5,
b: 6
}
This mode may break your scripts - e.g "return { a: 1 }" will be broken into two lines, so beware.
space_before_conditional (default true) - should the space before conditional statement be added, "if(true)" vs "if (true)",
unescape_strings (default false) - should printable characters in strings encoded in \xNN notation be unescaped, "example" vs "\x65\x78\x61\x6d\x70\x6c\x65"
e.g
js_beautify(js_source_text, {
'indent_size': 1,
'indent_char': '\t'
});
*/
function js_beautify(js_source_text, options) {
var input, output, token_text, last_type, last_text, last_last_text, last_word, flags, flag_store, indent_string;
var whitespace, wordchar, punct, parser_pos, line_starters, digits;
var prefix, token_type, do_block_just_closed;
var wanted_newline, just_added_newline, n_newlines;
var preindent_string = '';
// Some interpreters have unexpected results with foo = baz || bar;
options = options ? options : {};
var opt_brace_style;
// compatibility
if (options.space_after_anon_function !== undefined && options.jslint_happy === undefined) {
options.jslint_happy = options.space_after_anon_function;
}
if (options.braces_on_own_line !== undefined) { //graceful handling of deprecated option
opt_brace_style = options.braces_on_own_line ? "expand" : "collapse";
}
opt_brace_style = options.brace_style ? options.brace_style : (opt_brace_style ? opt_brace_style : "collapse");
var opt_indent_size = options.indent_size ? options.indent_size : 4,
opt_indent_char = options.indent_char ? options.indent_char : ' ',
opt_preserve_newlines = typeof options.preserve_newlines === 'undefined' ? true : options.preserve_newlines,
opt_break_chained_methods = typeof options.break_chained_methods === 'undefined' ? false : options.break_chained_methods,
opt_max_preserve_newlines = typeof options.max_preserve_newlines === 'undefined' ? false : options.max_preserve_newlines,
opt_jslint_happy = options.jslint_happy === 'undefined' ? false : options.jslint_happy,
opt_keep_array_indentation = typeof options.keep_array_indentation === 'undefined' ? false : options.keep_array_indentation,
opt_space_before_conditional = typeof options.space_before_conditional === 'undefined' ? true : options.space_before_conditional,
opt_unescape_strings = typeof options.unescape_strings === 'undefined' ? false : options.unescape_strings;
just_added_newline = false;
// cache the source's length.
var input_length = js_source_text.length;
function trim_output(eat_newlines) {
eat_newlines = typeof eat_newlines === 'undefined' ? false : eat_newlines;
while (output.length && (output[output.length - 1] === ' '
|| output[output.length - 1] === indent_string
|| output[output.length - 1] === preindent_string
|| (eat_newlines && (output[output.length - 1] === '\n' || output[output.length - 1] === '\r')))) {
output.pop();
}
}
function trim(s) {
return s.replace(/^\s\s*|\s\s*$/, '');
}
// we could use just string.split, but
// IE doesn't like returning empty strings
function split_newlines(s) {
//return s.split(/\x0d\x0a|\x0a/);
s = s.replace(/\x0d/g, '');
var out = [],
idx = s.indexOf("\n");
while (idx !== -1) {
out.push(s.substring(0, idx));
s = s.substring(idx + 1);
idx = s.indexOf("\n");
}
if (s.length) {
out.push(s);
}
return out;
}
function force_newline() {
var old_keep_array_indentation = opt_keep_array_indentation;
opt_keep_array_indentation = false;
print_newline();
opt_keep_array_indentation = old_keep_array_indentation;
}
function print_newline(ignore_repeated, reset_statement_flags) {
flags.eat_next_space = false;
if (opt_keep_array_indentation && is_array(flags.mode)) {
return;
}
ignore_repeated = typeof ignore_repeated === 'undefined' ? true : ignore_repeated;
reset_statement_flags = typeof reset_statement_flags === 'undefined' ? true : reset_statement_flags;
if (reset_statement_flags) {
flags.if_line = false;
flags.chain_extra_indentation = 0;
}
trim_output();
if (!output.length) {
return; // no newline on start of file
}
if (output[output.length - 1] !== "\n" || !ignore_repeated) {
just_added_newline = true;
output.push("\n");
}
if (preindent_string) {
output.push(preindent_string);
}
for (var i = 0; i < flags.indentation_level + flags.chain_extra_indentation; i += 1) {
output.push(indent_string);
}
if (flags.var_line && flags.var_line_reindented) {
output.push(indent_string); // skip space-stuffing, if indenting with a tab
}
}
function print_single_space() {
if (last_type === 'TK_COMMENT') {
return print_newline();
}
if (flags.eat_next_space) {
flags.eat_next_space = false;
return;
}
var last_output = ' ';
if (output.length) {
last_output = output[output.length - 1];
}
if (last_output !== ' ' && last_output !== '\n' && last_output !== indent_string) { // prevent occassional duplicate space
output.push(' ');
}
}
function print_token() {
just_added_newline = false;
flags.eat_next_space = false;
output.push(token_text);
}
function indent() {
flags.indentation_level += 1;
}
function remove_indent() {
if (output.length && output[output.length - 1] === indent_string) {
output.pop();
}
}
function set_mode(mode) {
if (flags) {
flag_store.push(flags);
}
flags = {
previous_mode: flags ? flags.mode : 'BLOCK',
mode: mode,
var_line: false,
var_line_tainted: false,
var_line_reindented: false,
in_html_comment: false,
if_line: false,
chain_extra_indentation: 0,
in_case_statement: false, // switch(..){ INSIDE HERE }
in_case: false, // we're on the exact line with "case 0:"
case_body: false, // the indented case-action block
eat_next_space: false,
indentation_level: (flags ? flags.indentation_level + ((flags.var_line && flags.var_line_reindented) ? 1 : 0) : 0),
ternary_depth: 0
};
}
function is_array(mode) {
return mode === '[EXPRESSION]' || mode === '[INDENTED-EXPRESSION]';
}
function is_expression(mode) {
return in_array(mode, ['[EXPRESSION]', '(EXPRESSION)', '(FOR-EXPRESSION)', '(COND-EXPRESSION)']);
}
function restore_mode() {
do_block_just_closed = flags.mode === 'DO_BLOCK';
if (flag_store.length > 0) {
var mode = flags.mode;
flags = flag_store.pop();
flags.previous_mode = mode;
}
}
function all_lines_start_with(lines, c) {
for (var i = 0; i < lines.length; i++) {
var line = trim(lines[i]);
if (line.charAt(0) !== c) {
return false;
}
}
return true;
}
function is_special_word(word) {
return in_array(word, ['case', 'return', 'do', 'if', 'throw', 'else']);
}
function in_array(what, arr) {
for (var i = 0; i < arr.length; i += 1) {
if (arr[i] === what) {
return true;
}
}
return false;
}
function look_up(exclude) {
var local_pos = parser_pos;
var c = input.charAt(local_pos);
while (in_array(c, whitespace) && c !== exclude) {
local_pos++;
if (local_pos >= input_length) {
return 0;
}
c = input.charAt(local_pos);
}
return c;
}
function get_next_token() {
var i;
var resulting_string;
n_newlines = 0;
if (parser_pos >= input_length) {
return ['', 'TK_EOF'];
}
wanted_newline = false;
var c = input.charAt(parser_pos);
parser_pos += 1;
var keep_whitespace = opt_keep_array_indentation && is_array(flags.mode);
if (keep_whitespace) {
var whitespace_count = 0;
while (in_array(c, whitespace)) {
if (c === "\n") {
trim_output();
output.push("\n");
just_added_newline = true;
whitespace_count = 0;
} else {
if (c === '\t') {
whitespace_count += 4;
} else if (c === '\r') {
// nothing
} else {
whitespace_count += 1;
}
}
if (parser_pos >= input_length) {
return ['', 'TK_EOF'];
}
c = input.charAt(parser_pos);
parser_pos += 1;
}
if (just_added_newline) {
for (i = 0; i < whitespace_count; i++) {
output.push(' ');
}
}
} else {
while (in_array(c, whitespace)) {
if (c === "\n") {
n_newlines += ((opt_max_preserve_newlines) ? (n_newlines <= opt_max_preserve_newlines) ? 1 : 0 : 1);
}
if (parser_pos >= input_length) {
return ['', 'TK_EOF'];
}
c = input.charAt(parser_pos);
parser_pos += 1;
}
if (opt_preserve_newlines) {
if (n_newlines > 1) {
for (i = 0; i < n_newlines; i += 1) {
print_newline(i === 0);
just_added_newline = true;
}
}
}
wanted_newline = n_newlines > 0;
}
if (in_array(c, wordchar)) {
if (parser_pos < input_length) {
while (in_array(input.charAt(parser_pos), wordchar)) {
c += input.charAt(parser_pos);
parser_pos += 1;
if (parser_pos === input_length) {
break;
}
}
}
// small and surprisingly unugly hack for 1E-10 representation
if (parser_pos !== input_length && c.match(/^[0-9]+[Ee]$/) && (input.charAt(parser_pos) === '-' || input.charAt(parser_pos) === '+')) {
var sign = input.charAt(parser_pos);
parser_pos += 1;
var t = get_next_token();
c += sign + t[0];
return [c, 'TK_WORD'];
}
if (c === 'in') { // hack for 'in' operator
return [c, 'TK_OPERATOR'];
}
if (wanted_newline && last_type !== 'TK_OPERATOR'
&& last_type !== 'TK_EQUALS'
&& !flags.if_line && (opt_preserve_newlines || last_text !== 'var')) {
print_newline();
}
return [c, 'TK_WORD'];
}
if (c === '(' || c === '[') {
return [c, 'TK_START_EXPR'];
}
if (c === ')' || c === ']') {
return [c, 'TK_END_EXPR'];
}
if (c === '{') {
return [c, 'TK_START_BLOCK'];
}
if (c === '}') {
return [c, 'TK_END_BLOCK'];
}
if (c === ';') {
return [c, 'TK_SEMICOLON'];
}
if (c === '/') {
var comment = '';
// peek for comment /* ... */
var inline_comment = true;
if (input.charAt(parser_pos) === '*') {
parser_pos += 1;
if (parser_pos < input_length) {
while (parser_pos < input_length &&
! (input.charAt(parser_pos) === '*' && input.charAt(parser_pos + 1) && input.charAt(parser_pos + 1) === '/')) {
c = input.charAt(parser_pos);
comment += c;
if (c === "\n" || c === "\r") {
inline_comment = false;
}
parser_pos += 1;
if (parser_pos >= input_length) {
break;
}
}
}
parser_pos += 2;
if (inline_comment && n_newlines === 0) {
return ['/*' + comment + '*/', 'TK_INLINE_COMMENT'];
} else {
return ['/*' + comment + '*/', 'TK_BLOCK_COMMENT'];
}
}
// peek for comment // ...
if (input.charAt(parser_pos) === '/') {
comment = c;
while (input.charAt(parser_pos) !== '\r' && input.charAt(parser_pos) !== '\n') {
comment += input.charAt(parser_pos);
parser_pos += 1;
if (parser_pos >= input_length) {
break;
}
}
if (wanted_newline) {
print_newline();
}
return [comment, 'TK_COMMENT'];
}
}
if (c === "'" || // string
c === '"' || // string
(c === '/' &&
((last_type === 'TK_WORD' && is_special_word(last_text)) ||
(last_text === ')' && in_array(flags.previous_mode, ['(COND-EXPRESSION)', '(FOR-EXPRESSION)'])) ||
(last_type === 'TK_COMMA' || last_type === 'TK_COMMENT' || last_type === 'TK_START_EXPR' || last_type === 'TK_START_BLOCK' || last_type === 'TK_END_BLOCK' || last_type === 'TK_OPERATOR' || last_type === 'TK_EQUALS' || last_type === 'TK_EOF' || last_type === 'TK_SEMICOLON')))) { // regexp
var sep = c;
var esc = false;
var esc1 = 0;
var esc2 = 0;
resulting_string = c;
if (parser_pos < input_length) {
if (sep === '/') {
//
// handle regexp separately...
//
var in_char_class = false;
while (esc || in_char_class || input.charAt(parser_pos) !== sep) {
resulting_string += input.charAt(parser_pos);
if (!esc) {
esc = input.charAt(parser_pos) === '\\';
if (input.charAt(parser_pos) === '[') {
in_char_class = true;
} else if (input.charAt(parser_pos) === ']') {
in_char_class = false;
}
} else {
esc = false;
}
parser_pos += 1;
if (parser_pos >= input_length) {
// incomplete string/rexp when end-of-file reached.
// bail out with what had been received so far.
return [resulting_string, 'TK_STRING'];
}
}
} else {
//
// and handle string also separately
//
while (esc || input.charAt(parser_pos) !== sep) {
resulting_string += input.charAt(parser_pos);
if (esc1 && esc1 >= esc2) {
esc1 = parseInt(resulting_string.substr(-esc2), 16);
if (esc1 && esc1 >= 0x20 && esc1 <= 0x7e) {
esc1 = String.fromCharCode(esc1);
resulting_string = resulting_string.substr(0, resulting_string.length - esc2 - 2) + (((esc1 === sep) || (esc1 === '\\')) ? '\\' : '') + esc1;
}
esc1 = 0;
}
if (esc1) {
esc1++;
} else if (!esc) {
esc = input.charAt(parser_pos) === '\\';
} else {
esc = false;
if (opt_unescape_strings) {
if (input.charAt(parser_pos) === 'x') {
esc1++;
esc2 = 2;
} else if (input.charAt(parser_pos) === 'u') {
esc1++;
esc2 = 4;
}
}
}
parser_pos += 1;
if (parser_pos >= input_length) {
// incomplete string/rexp when end-of-file reached.
// bail out with what had been received so far.
return [resulting_string, 'TK_STRING'];
}
}
}
}
parser_pos += 1;
resulting_string += sep;
if (sep === '/') {
// regexps may have modifiers /regexp/MOD , so fetch those, too
while (parser_pos < input_length && in_array(input.charAt(parser_pos), wordchar)) {
resulting_string += input.charAt(parser_pos);
parser_pos += 1;
}
}
return [resulting_string, 'TK_STRING'];
}
if (c === '#') {
if (output.length === 0 && input.charAt(parser_pos) === '!') {
// shebang
resulting_string = c;
while (parser_pos < input_length && c !== '\n') {
c = input.charAt(parser_pos);
resulting_string += c;
parser_pos += 1;
}
output.push(trim(resulting_string) + '\n');
print_newline();
return get_next_token();
}
// Spidermonkey-specific sharp variables for circular references
// https://developer.mozilla.org/En/Sharp_variables_in_JavaScript
// https://mxr.mozilla.org/mozilla-central/source/js/src/jsscan.cpp around line 1935
var sharp = '#';
if (parser_pos < input_length && in_array(input.charAt(parser_pos), digits)) {
do {
c = input.charAt(parser_pos);
sharp += c;
parser_pos += 1;
} while (parser_pos < input_length && c !== '#' && c !== '=');
if (c === '#') {
//
} else if (input.charAt(parser_pos) === '[' && input.charAt(parser_pos + 1) === ']') {
sharp += '[]';
parser_pos += 2;
} else if (input.charAt(parser_pos) === '{' && input.charAt(parser_pos + 1) === '}') {
sharp += '{}';
parser_pos += 2;
}
return [sharp, 'TK_WORD'];
}
}
if (c === '<' && input.substring(parser_pos - 1, parser_pos + 3) === '<!--') {
parser_pos += 3;
c = '<!--';
while (input.charAt(parser_pos) !== '\n' && parser_pos < input_length) {
c += input.charAt(parser_pos);
parser_pos++;
}
flags.in_html_comment = true;
return [c, 'TK_COMMENT'];
}
if (c === '-' && flags.in_html_comment && input.substring(parser_pos - 1, parser_pos + 2) === '-->') {
flags.in_html_comment = false;
parser_pos += 2;
if (wanted_newline) {
print_newline();
}
return ['-->', 'TK_COMMENT'];
}
if (c === '.') {
return [c, 'TK_DOT'];
}
if (in_array(c, punct)) {
while (parser_pos < input_length && in_array(c + input.charAt(parser_pos), punct)) {
c += input.charAt(parser_pos);
parser_pos += 1;
if (parser_pos >= input_length) {
break;
}
}
if (c === ',') {
return [c, 'TK_COMMA'];
} else if (c === '=') {
return [c, 'TK_EQUALS'];
} else {
return [c, 'TK_OPERATOR'];
}
}
return [c, 'TK_UNKNOWN'];
}
//----------------------------------
indent_string = '';
while (opt_indent_size > 0) {
indent_string += opt_indent_char;
opt_indent_size -= 1;
}
while (js_source_text && (js_source_text.charAt(0) === ' ' || js_source_text.charAt(0) === '\t')) {
preindent_string += js_source_text.charAt(0);
js_source_text = js_source_text.substring(1);
}
input = js_source_text;
last_word = ''; // last 'TK_WORD' passed
last_type = 'TK_START_EXPR'; // last token type
last_text = ''; // last token text
last_last_text = ''; // pre-last token text
output = [];
do_block_just_closed = false;
whitespace = "\n\r\t ".split('');
wordchar = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_$'.split('');
digits = '0123456789'.split('');
punct = '+ - * / % & ++ -- = += -= *= /= %= == === != !== > < >= <= >> << >>> >>