Socket
Socket
Sign inDemoInstall

@bbob/parser

Package Overview
Dependencies
Maintainers
1
Versions
53
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@bbob/parser - npm Package Compare versions

Comparing version 2.5.8 to 2.6.0

dist/index.html
es/lexer_old.js
lib/lexer_old.js
src/lexer_old.js

11

CHANGELOG.md

@@ -6,2 +6,13 @@ # Change Log

# [2.6.0](https://github.com/JiLiZART/bbob/compare/v2.5.8...v2.6.0) (2020-12-10)
### Features
* **parser:** rewrite lexer to make it faster ([#50](https://github.com/JiLiZART/bbob/issues/50)) ([772d422](https://github.com/JiLiZART/bbob/commit/772d422d770b0f7716a86ac82c10eb3baaf77828))
## [2.5.8](https://github.com/JiLiZART/bbob/compare/v2.5.7...v2.5.8) (2020-07-08)

@@ -8,0 +19,0 @@

821

dist/index.js

@@ -88,2 +88,6 @@ (function (global, factory) {

var keysReduce = function keysReduce(obj, reduce, def) {
return Object.keys(obj).reduce(reduce, def);
};
var getNodeLength = function getNodeLength(node) {

@@ -164,7 +168,7 @@ if (isTagNode(node)) {

// To avoid some malformed attributes
if (typeof values === 'undefined') {
if (values == null) {
return '';
}
return Object.keys(values).reduce(function (arr, key) {
return keysReduce(values, function (arr, key) {
return [].concat(arr, [attrValue(key, values[key])]);

@@ -185,3 +189,3 @@ }, ['']).join(' ');

var getUniqAttr = function getUniqAttr(attrs) {
return Object.keys(attrs).reduce(function (res, key) {
return keysReduce(attrs, function (res, key) {
return attrs[key] === key ? attrs[key] : null;

@@ -270,3 +274,3 @@ }, null);

this.attrs = attrs;
this.content = [].concat(content);
this.content = Array.isArray(content) ? content : [content];
}

@@ -343,204 +347,23 @@

var char_1$1 = createCommonjsModule(function (module, exports) {
var TOKEN_TYPE_ID = 'type'; // 0;
exports.__esModule = true;
exports.BACKSLASH = exports.PLACEHOLDER_SPACE = exports.PLACEHOLDER_SPACE_TAB = exports.SLASH = exports.CLOSE_BRAKET = exports.OPEN_BRAKET = exports.SPACE = exports.QUOTEMARK = exports.EQ = exports.TAB = exports.R = exports.F = exports.N = void 0;
var N = '\n';
exports.N = N;
var TAB = '\t';
exports.TAB = TAB;
var F = '\f';
exports.F = F;
var R = '\r';
exports.R = R;
var EQ = '=';
exports.EQ = EQ;
var QUOTEMARK = '"';
exports.QUOTEMARK = QUOTEMARK;
var SPACE = ' ';
exports.SPACE = SPACE;
var OPEN_BRAKET = '[';
exports.OPEN_BRAKET = OPEN_BRAKET;
var CLOSE_BRAKET = ']';
exports.CLOSE_BRAKET = CLOSE_BRAKET;
var SLASH = '/';
exports.SLASH = SLASH;
var BACKSLASH = '\\';
exports.BACKSLASH = BACKSLASH;
var PLACEHOLDER_SPACE_TAB = ' ';
exports.PLACEHOLDER_SPACE_TAB = PLACEHOLDER_SPACE_TAB;
var PLACEHOLDER_SPACE = ' '; // const getChar = String.fromCharCode;
var TOKEN_VALUE_ID = 'value'; // 1;
exports.PLACEHOLDER_SPACE = PLACEHOLDER_SPACE;
});
var TOKEN_COLUMN_ID = 'row'; // 2;
unwrapExports(char_1$1);
var char_2$1 = char_1$1.BACKSLASH;
var char_3$1 = char_1$1.PLACEHOLDER_SPACE;
var char_4$1 = char_1$1.PLACEHOLDER_SPACE_TAB;
var char_5$1 = char_1$1.SLASH;
var char_6$1 = char_1$1.CLOSE_BRAKET;
var char_7$1 = char_1$1.OPEN_BRAKET;
var char_8$1 = char_1$1.SPACE;
var char_9$1 = char_1$1.QUOTEMARK;
var char_10$1 = char_1$1.EQ;
var char_11$1 = char_1$1.TAB;
var char_12$1 = char_1$1.R;
var char_13$1 = char_1$1.F;
var char_14$1 = char_1$1.N;
var TOKEN_LINE_ID = 'line'; // 3;
var es = createCommonjsModule(function (module, exports) {
var TOKEN_TYPE_WORD = 1; // 'word';
exports.__esModule = true;
exports.isEOL = exports.isStringNode = exports.isTagNode = exports.getUniqAttr = exports.getNodeLength = exports.escapeHTML = exports.appendToNode = exports.attrValue = exports.attrsToString = void 0;
var TOKEN_TYPE_TAG = 2; // 'tag';
var TOKEN_TYPE_ATTR_NAME = 3; // 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 4; // 'attr-value';
var isTagNode = function isTagNode(el) {
return typeof el === 'object' && !!el.tag;
};
var TOKEN_TYPE_SPACE = 5; // 'space';
exports.isTagNode = isTagNode;
var TOKEN_TYPE_NEW_LINE = 6; // 'new-line';
var isStringNode = function isStringNode(el) {
return typeof el === 'string';
};
exports.isStringNode = isStringNode;
var isEOL = function isEOL(el) {
return el === char_1$1.N;
};
exports.isEOL = isEOL;
var getNodeLength = function getNodeLength(node) {
if (isTagNode(node)) {
return node.content.reduce(function (count, contentNode) {
return count + getNodeLength(contentNode);
}, 0);
}
if (isStringNode(node)) {
return node.length;
}
return 0;
};
/**
* Appends value to Tag Node
* @param {TagNode} node
* @param value
*/
exports.getNodeLength = getNodeLength;
var appendToNode = function appendToNode(node, value) {
node.content.push(value);
};
/**
* Replaces " to &qquot;
* @param {String} value
*/
exports.appendToNode = appendToNode;
var escapeHTML = function escapeHTML(value) {
return value.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;').replace(/"/g, '&quot;').replace(/'/g, '&#039;') // eslint-disable-next-line no-script-url
.replace(/(javascript):/gi, '$1%3A');
};
/**
* Acept name and value and return valid html5 attribute string
* @param {String} name
* @param {String} value
* @return {string}
*/
exports.escapeHTML = escapeHTML;
var attrValue = function attrValue(name, value) {
var type = typeof value;
var types = {
boolean: function boolean() {
return value ? "" + name : '';
},
number: function number() {
return name + "=\"" + value + "\"";
},
string: function string() {
return name + "=\"" + escapeHTML(value) + "\"";
},
object: function object() {
return name + "=\"" + escapeHTML(JSON.stringify(value)) + "\"";
}
};
return types[type] ? types[type]() : '';
};
/**
* Transforms attrs to html params string
* @param values
*/
exports.attrValue = attrValue;
var attrsToString = function attrsToString(values) {
// To avoid some malformed attributes
if (typeof values === 'undefined') {
return '';
}
return Object.keys(values).reduce(function (arr, key) {
return [].concat(arr, [attrValue(key, values[key])]);
}, ['']).join(' ');
};
/**
* Gets value from
* @example
* getUniqAttr({ 'foo': true, 'bar': bar' }) => 'bar'
* @param attrs
* @returns {string}
*/
exports.attrsToString = attrsToString;
var getUniqAttr = function getUniqAttr(attrs) {
return Object.keys(attrs).reduce(function (res, key) {
return attrs[key] === key ? attrs[key] : null;
}, null);
};
exports.getUniqAttr = getUniqAttr;
});
unwrapExports(es);
var es_1 = es.isEOL;
var es_2 = es.isStringNode;
var es_3 = es.isTagNode;
var es_4 = es.getUniqAttr;
var es_5 = es.getNodeLength;
var es_6 = es.escapeHTML;
var es_7 = es.appendToNode;
var es_8 = es.attrValue;
var es_9 = es.attrsToString;
var TOKEN_TYPE_ID = 'type'; // 0;
var TOKEN_VALUE_ID = 'value'; // 1;
var TOKEN_COLUMN_ID = 'row'; // 2;
var TOKEN_LINE_ID = 'line'; // 3;
var TOKEN_TYPE_WORD = 'word';
var TOKEN_TYPE_TAG = 'tag';
var TOKEN_TYPE_ATTR_NAME = 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 'attr-value';
var TOKEN_TYPE_SPACE = 'space';
var TOKEN_TYPE_NEW_LINE = 'new-line';
/**
* @param {Token} token

@@ -648,3 +471,3 @@ * @returns {string}

function Token(type, value, line, row) {
this[TOKEN_TYPE_ID] = String(type);
this[TOKEN_TYPE_ID] = Number(type);
this[TOKEN_VALUE_ID] = String(value);

@@ -658,3 +481,4 @@ this[TOKEN_LINE_ID] = Number(line);

_proto.isEmpty = function isEmpty() {
return !!this[TOKEN_TYPE_ID];
// eslint-disable-next-line no-restricted-globals
return isNaN(this[TOKEN_TYPE_ID]);
};

@@ -715,106 +539,136 @@

/**
* @typedef {Object} CharGrabber
* @property {Function} skip
* @property {Function} hasNext
* @property {Function} isLast
* @property {Function} grabWhile
*/
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @returns
*/
var createCharGrabber = function createCharGrabber(source, options) {
// let idx = 0;
function CharGrabber(source, options) {
var cursor = {
pos: 0,
length: source.length
len: source.length
};
var skip = function skip() {
cursor.pos += 1;
var substrUntilChar = function substrUntilChar(char) {
var pos = cursor.pos;
var idx = source.indexOf(char, pos);
return idx >= 0 ? source.substr(pos, idx - pos) : '';
};
if (options && options.onSkip) {
options.onSkip();
}
var includes = function includes(val) {
return source.indexOf(val, cursor.pos) >= 0;
};
var hasNext = function hasNext() {
return cursor.length > cursor.pos;
return cursor.len > cursor.pos;
};
var getRest = function getRest() {
var isLast = function isLast() {
return cursor.pos === cursor.len;
};
var skip = function skip(num, silent) {
if (num === void 0) {
num = 1;
}
cursor.pos += num;
if (options && options.onSkip && !silent) {
options.onSkip();
}
};
var rest = function rest() {
return source.substr(cursor.pos);
};
var getCurr = function getCurr() {
var curr = function curr() {
return source[cursor.pos];
};
return {
skip: skip,
hasNext: hasNext,
isLast: function isLast() {
return cursor.pos === cursor.length;
},
var prev = function prev() {
var prevPos = cursor.pos - 1;
return typeof source[prevPos] !== 'undefined' ? source[prevPos] : null;
};
/**
* @param {Function} cond
* @returns {string}
*/
grabWhile: function grabWhile(cond) {
var start = 0;
var next = function next() {
var nextPos = cursor.pos + 1;
return nextPos <= source.length - 1 ? source[nextPos] : null;
};
if (hasNext()) {
start = cursor.pos;
var grabWhile = function grabWhile(cond, silent) {
var start = 0;
while (hasNext() && cond(getCurr())) {
skip();
}
if (hasNext()) {
start = cursor.pos;
while (hasNext() && cond(curr())) {
skip(1, silent);
}
}
return source.substr(start, cursor.pos - start);
},
getNext: function getNext() {
var nextPos = cursor.pos + 1;
return source.substr(start, cursor.pos - start);
};
/**
* @type {skip}
*/
if (nextPos <= source.length - 1) {
return source[nextPos];
}
return null;
},
getPrev: function getPrev() {
var prevPos = cursor.pos - 1;
this.skip = skip;
/**
* @returns {Boolean}
*/
if (typeof source[prevPos] !== 'undefined') {
return source[prevPos];
}
this.hasNext = hasNext;
/**
* @returns {String}
*/
return null;
},
getCurr: getCurr,
getRest: getRest,
this.getCurr = curr;
/**
* @returns {String}
*/
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
substrUntilChar: function substrUntilChar(char) {
var restStr = getRest();
var indexOfChar = restStr.indexOf(char);
this.getRest = rest;
/**
* @returns {String}
*/
if (indexOfChar >= 0) {
return restStr.substr(0, indexOfChar);
}
this.getNext = next;
/**
* @returns {String}
*/
return '';
}
};
this.getPrev = prev;
/**
* @returns {Boolean}
*/
this.isLast = isLast;
/**
* @returns {Boolean}
*/
this.includes = includes;
/**
* @param {Function} cond
* @param {Boolean} silent
* @return {String}
*/
this.grabWhile = grabWhile;
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
this.substrUntilChar = substrUntilChar;
}
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @return CharGrabber
*/
var createCharGrabber = function createCharGrabber(source, options) {
return new CharGrabber(source, options);
};

@@ -852,18 +706,4 @@ /**

};
/**
* @typedef {Object} ItemList
* @type {Object}
* @property {getLastCb} getLast
* @property {flushLastCb} flushLast
* @property {pushCb} push
* @property {toArrayCb} toArray
*/
/**
*
* @param values
* @return {ItemList}
*/
var createList = function createList(values) {
function NodeList(values) {
if (values === void 0) {

@@ -874,49 +714,37 @@ values = [];

var nodes = values;
/**
* @callback getLastCb
*/
var getLast = function getLast() {
if (Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined') {
return nodes[nodes.length - 1];
}
return null;
return Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined' ? nodes[nodes.length - 1] : null;
};
/**
* @callback flushLastCb
* @return {*}
*/
var flushLast = function flushLast() {
if (nodes.length) {
return nodes.pop();
}
return false;
return nodes.length ? nodes.pop() : false;
};
/**
* @callback pushCb
* @param value
*/
var push = function push(value) {
return nodes.push(value);
};
/**
* @callback toArrayCb
* @return {Array}
*/
var toArray = function toArray() {
return nodes;
};
return {
getLast: getLast,
flushLast: flushLast,
push: push,
toArray: function toArray() {
return nodes;
}
};
this.push = push;
this.toArray = toArray;
this.getLast = getLast;
this.flushLast = flushLast;
}
/**
*
* @param values
* @return {NodeList}
*/
var createList = function createList(values) {
if (values === void 0) {
values = [];
}
return new NodeList(values);
};

@@ -929,3 +757,3 @@

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -969,9 +797,20 @@ * @param {Number} r line number

var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_TAG_ATTRS = 2;
var TAG_STATE_NAME = 0;
var TAG_STATE_ATTR = 1;
var TAG_STATE_VALUE = 2;
var row = 0;
var col = 0;
var tokenIndex = -1;
var stateMode = STATE_WORD;
var tagMode = TAG_STATE_NAME;
var tokens = new Array(Math.floor(buffer.length));
var openTag = options.openTag || char_7;
var closeTag = options.closeTag || char_6;
var escapeTags = options.enableEscapeTags;
var escapeTags = !!options.enableEscapeTags;
var onToken = options.onToken || function () {};
var RESERVED_CHARS = [closeTag, openTag, char_9, char_2, char_8, char_11, char_10, char_14, EM];

@@ -987,2 +826,6 @@ var NOT_CHAR_TOKENS = [// ...(options.enableEscapeTags ? [BACKSLASH] : []),

var isNewLine = function isNewLine(char) {
return char === char_14;
};
var isWhiteSpace = function isWhiteSpace(char) {

@@ -1007,160 +850,244 @@ return WHITESPACES.indexOf(char) >= 0;

};
var onSkip = function onSkip() {
col++;
};
var unq = function unq(val) {
return unquote(trimChar(val, char_9));
};
var chars = createCharGrabber(buffer, {
onSkip: onSkip
});
/**
* Emits newly created token to subscriber
* @param token
* @param {Number} type
* @param {String} value
*/
var emitToken = function emitToken(token) {
if (options.onToken) {
options.onToken(token);
}
function emitToken(type, value) {
var token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
};
/**
* Parses params inside [myTag---params goes here---]content[/myTag]
* @param str
* @returns {{tag: *, attrs: Array}}
*/
}
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_ATTR) {
var validAttrName = function validAttrName(char) {
return !(char === char_10 || isWhiteSpace(char));
};
var parseAttrs = function parseAttrs(str) {
var tagName = null;
var skipSpecialChars = false;
var attrTokens = [];
var attrCharGrabber = createCharGrabber(str);
var _name = tagChars.grabWhile(validAttrName);
var validAttr = function validAttr(char) {
var isEQ = char === char_10;
var isWS = isWhiteSpace(char);
var prevChar = attrCharGrabber.getPrev();
var nextChar = attrCharGrabber.getNext();
var isPrevSLASH = prevChar === char_2;
var isTagNameEmpty = tagName === null;
var isEnd = tagChars.isLast();
var isValue = tagChars.getCurr() !== char_10;
tagChars.skip();
if (isTagNameEmpty) {
return (isEQ || isWS || attrCharGrabber.isLast()) === false;
if (isEnd || isValue) {
emitToken(TYPE_ATTR_VALUE, unq(_name));
} else {
emitToken(TYPE_ATTR_NAME, _name);
}
if (skipSpecialChars && isSpecialChar(char)) {
return true;
if (isEnd) {
return TAG_STATE_NAME;
}
if (char === char_9 && !isPrevSLASH) {
skipSpecialChars = !skipSpecialChars;
if (isValue) {
return TAG_STATE_ATTR;
}
if (!skipSpecialChars && !(nextChar === char_10 || isWhiteSpace(nextChar))) {
return false;
return TAG_STATE_VALUE;
}
if (tagMode === TAG_STATE_VALUE) {
var stateSpecial = false;
var validAttrValue = function validAttrValue(char) {
// const isEQ = char === EQ;
var isQM = char === char_9;
var prevChar = tagChars.getPrev();
var nextChar = tagChars.getNext();
var isPrevSLASH = prevChar === char_2;
var isNextEQ = nextChar === char_10;
var isWS = isWhiteSpace(char); // const isPrevWS = isWhiteSpace(prevChar);
var isNextWS = isWhiteSpace(nextChar);
if (stateSpecial && isSpecialChar(char)) {
return true;
}
}
return (isEQ || isWS) === false;
};
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
var nextAttr = function nextAttr() {
var attrStr = attrCharGrabber.grabWhile(validAttr);
var currChar = attrCharGrabber.getCurr(); // first string before space is a tag name [tagName params...]
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (tagName === null) {
tagName = attrStr;
} else if (isWhiteSpace(currChar) || currChar === char_9 || !attrCharGrabber.hasNext()) {
var escaped = unquote(trimChar(attrStr, char_9));
attrTokens.push(createToken(TYPE_ATTR_VALUE, escaped, row, col));
} else {
attrTokens.push(createToken(TYPE_ATTR_NAME, attrStr, row, col));
if (!isSingleValueTag) {
return isWS === false; // return (isEQ || isWS) === false;
}
return true;
};
var _name2 = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(TYPE_ATTR_VALUE, unq(_name2));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
attrCharGrabber.skip();
};
while (attrCharGrabber.hasNext()) {
nextAttr();
return TAG_STATE_ATTR;
}
return {
tag: tagName,
attrs: attrTokens
var validName = function validName(char) {
return !(char === char_10 || isWhiteSpace(char) || tagChars.isLast());
};
};
var bufferGrabber = createCharGrabber(buffer, {
onSkip: function onSkip() {
col++;
var name = tagChars.grabWhile(validName);
emitToken(TYPE_TAG, name);
tagChars.skip(); // in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
});
var next = function next() {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
var hasEQ = tagChars.includes(char_10);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
if (currChar === char_14) {
bufferGrabber.skip();
col = 0;
row++;
emitToken(createToken(TYPE_NEW_LINE, currChar, row, col));
} else if (isWhiteSpace(currChar)) {
var str = bufferGrabber.grabWhile(isWhiteSpace);
emitToken(createToken(TYPE_SPACE, str, row, col));
} else if (escapeTags && isEscapeChar(currChar) && isEscapableChar(nextChar)) {
bufferGrabber.skip(); // skip the \ without emitting anything
function stateTag() {
var currChar = chars.getCurr();
bufferGrabber.skip(); // skip past the [, ] or \ as well
if (currChar === openTag) {
var nextChar = chars.getNext();
chars.skip(); // detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
emitToken(createToken(TYPE_WORD, nextChar, row, col));
} else if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var substr = bufferGrabber.substrUntilChar(closeTag);
var substr = chars.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else {
var _str = bufferGrabber.grabWhile(function (val) {
return val !== closeTag;
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(TYPE_WORD, currChar);
return STATE_WORD;
} // [myTag ]
var isNoAttrsInTag = substr.indexOf(char_10) === -1; // [/myTag]
var isClosingTag = substr[0] === char_5;
if (isNoAttrsInTag || isClosingTag) {
var name = chars.grabWhile(function (char) {
return char !== closeTag;
});
chars.skip(); // skip closeTag
bufferGrabber.skip(); // skip closeTag
// [myTag ]
emitToken(TYPE_TAG, name);
return STATE_WORD;
}
var isNoAttrsInTag = _str.indexOf(char_10) === -1; // [/myTag]
return STATE_TAG_ATTRS;
}
var isClosingTag = _str[0] === char_5;
return STATE_WORD;
}
if (isNoAttrsInTag || isClosingTag) {
emitToken(createToken(TYPE_TAG, _str, row, col));
} else {
var parsed = parseAttrs(_str);
emitToken(createToken(TYPE_TAG, parsed.tag, row, col));
parsed.attrs.map(emitToken);
}
function stateAttrs() {
var silent = true;
var tagStr = chars.grabWhile(function (char) {
return char !== closeTag;
}, silent);
var tagGrabber = createCharGrabber(tagStr, {
onSkip: onSkip
});
var hasSpace = tagGrabber.includes(char_8);
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
chars.skip(); // skip closeTag
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
return STATE_WORD;
}
if (isWhiteSpace(chars.getCurr())) {
emitToken(TYPE_SPACE, chars.grabWhile(isWhiteSpace));
return STATE_WORD;
}
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
} else if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else if (isCharToken(currChar)) {
if (escapeTags && isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else {
var _str2 = bufferGrabber.grabWhile(function (char) {
if (escapeTags) {
return isCharToken(char) && !isEscapeChar(char);
}
emitToken(TYPE_WORD, chars.getCurr());
chars.skip();
return STATE_WORD;
}
return isCharToken(char);
});
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
var currChar = chars.getCurr();
var nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
emitToken(createToken(TYPE_WORD, _str2, row, col));
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
emitToken(TYPE_WORD, nextChar);
return STATE_WORD;
}
emitToken(TYPE_WORD, currChar);
return STATE_WORD;
}
var isChar = function isChar(char) {
return isCharToken(char) && !isEscapeChar(char);
};
emitToken(TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
};
var tokenize = function tokenize() {
while (bufferGrabber.hasNext()) {
next();
emitToken(TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
case STATE_WORD:
stateMode = stateWord();
break;
default:
stateMode = STATE_WORD;
break;
}
}

@@ -1170,9 +1097,9 @@

return tokens;
};
}
var isTokenNested = function isTokenNested(token) {
function isTokenNested(token) {
var value = openTag + char_5 + token.getValue(); // potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -1207,3 +1134,3 @@ return {

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -1215,3 +1142,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -1223,3 +1150,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -1231,3 +1158,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -1310,3 +1237,3 @@

if (Array.isArray(items)) {
if (es_3(node)) {
if (lib_3(node)) {
if (isAllowedTag(node.tag)) {

@@ -1313,0 +1240,0 @@ items.push(node.toTagNode());

2

dist/index.min.js

@@ -1,1 +0,1 @@

!function(t,e){"object"==typeof exports&&"undefined"!=typeof module?e(exports):"function"==typeof define&&define.amd?define(["exports"],e):e((t=t||self).BbobParser={})}(this,(function(t){"use strict";function e(t){return t&&t.__esModule&&Object.prototype.hasOwnProperty.call(t,"default")?t.default:t}function n(t,e){return t(e={exports:{}},e.exports),e.exports}var r=n((function(t,e){e.__esModule=!0,e.BACKSLASH=e.PLACEHOLDER_SPACE=e.PLACEHOLDER_SPACE_TAB=e.SLASH=e.CLOSE_BRAKET=e.OPEN_BRAKET=e.SPACE=e.QUOTEMARK=e.EQ=e.TAB=e.R=e.F=e.N=void 0;e.N="\n";e.TAB="\t";e.F="\f";e.R="\r";e.EQ="=";e.QUOTEMARK='"';e.SPACE=" ";e.OPEN_BRAKET="[";e.CLOSE_BRAKET="]";e.SLASH="/";e.BACKSLASH="\\";e.PLACEHOLDER_SPACE_TAB=" ";e.PLACEHOLDER_SPACE=" "}));e(r);var o=r.BACKSLASH,i=r.SLASH,u=r.CLOSE_BRAKET,a=r.OPEN_BRAKET,s=r.SPACE,c=r.QUOTEMARK,f=r.EQ,l=r.TAB,g=r.N,p=n((function(t,e){e.__esModule=!0,e.isEOL=e.isStringNode=e.isTagNode=e.getUniqAttr=e.getNodeLength=e.escapeHTML=e.appendToNode=e.attrValue=e.attrsToString=void 0;var n=function(t){return"object"==typeof t&&!!t.tag};e.isTagNode=n;var o=function(t){return"string"==typeof t};e.isStringNode=o;e.isEOL=function(t){return t===r.N};e.getNodeLength=function t(e){return n(e)?e.content.reduce((function(e,n){return e+t(n)}),0):o(e)?e.length:0};e.appendToNode=function(t,e){t.content.push(e)};var i=function(t){return t.replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/>/g,"&gt;").replace(/"/g,"&quot;").replace(/'/g,"&#039;").replace(/(javascript):/gi,"$1%3A")};e.escapeHTML=i;var u=function(t,e){var n=typeof e,r={boolean:function(){return e?""+t:""},number:function(){return t+'="'+e+'"'},string:function(){return t+'="'+i(e)+'"'},object:function(){return t+'="'+i(JSON.stringify(e))+'"'}};return r[n]?r[n]():""};e.attrValue=u;e.attrsToString=function(t){return void 0===t?"":Object.keys(t).reduce((function(e,n){return[].concat(e,[u(n,t[n])])}),[""]).join(" ")};e.getUniqAttr=function(t){return Object.keys(t).reduce((function(e,n){return t[n]===n?t[n]:null}),null)}}));e(p);var d=n((function(t,e){function n(t,e){for(var n=0;e.length>n;n++){var r=e[n];r.enumerable=r.enumerable||!1,r.configurable=!0,"value"in r&&(r.writable=!0),Object.defineProperty(t,r.key,r)}}function o(){return(o=Object.assign||function(t){for(var e=1;arguments.length>e;e++){var n=arguments[e];for(var r in n)Object.prototype.hasOwnProperty.call(n,r)&&(t[r]=n[r])}return t}).apply(this,arguments)}e.__esModule=!0,e.default=e.TagNode=void 0;var i=function(){function t(t,e,n){this.tag=t,this.attrs=e,this.content=[].concat(n)}var e,i,u,a=t.prototype;return a.attr=function(t,e){return void 0!==e&&(this.attrs[t]=e),this.attrs[t]},a.append=function(t){return(0,p.appendToNode)(this,t)},a.toTagNode=function(){return new t(this.tag.toLowerCase(),this.attrs,this.content)},a.toString=function(){var t=r.OPEN_BRAKET,e=r.CLOSE_BRAKET,n=0===this.content.length,i=this.content.reduce((function(t,e){return t+""+e}),""),u=function(t,e){var n=(0,p.getUniqAttr)(e);if(n){var r=(0,p.attrValue)(t,n),i=o({},e);return delete i[n],""+r+(0,p.attrsToString)(i)}return""+t+(0,p.attrsToString)(e)}(this.tag,this.attrs);return n?""+t+u+e:""+t+u+e+i+t+r.SLASH+this.tag+e},e=t,(i=[{key:"length",get:function(){return(0,p.getNodeLength)(this)}}])&&n(e.prototype,i),u&&n(e,u),t}();e.TagNode=i,i.create=function(t,e,n){return void 0===e&&(e={}),void 0===n&&(n=[]),new i(t,e,n)},i.isOf=function(t,e){return t.tag===e},e.default=i})),h=e(d),v=d.TagNode,A=n((function(t,e){e.__esModule=!0,e.BACKSLASH=e.PLACEHOLDER_SPACE=e.PLACEHOLDER_SPACE_TAB=e.SLASH=e.CLOSE_BRAKET=e.OPEN_BRAKET=e.SPACE=e.QUOTEMARK=e.EQ=e.TAB=e.R=e.F=e.N=void 0;e.N="\n";e.TAB="\t";e.F="\f";e.R="\r";e.EQ="=";e.QUOTEMARK='"';e.SPACE=" ";e.OPEN_BRAKET="[";e.CLOSE_BRAKET="]";e.SLASH="/";e.BACKSLASH="\\";e.PLACEHOLDER_SPACE_TAB=" ";e.PLACEHOLDER_SPACE=" "}));e(A);var T=n((function(t,e){e.__esModule=!0,e.isEOL=e.isStringNode=e.isTagNode=e.getUniqAttr=e.getNodeLength=e.escapeHTML=e.appendToNode=e.attrValue=e.attrsToString=void 0;var n=function(t){return"object"==typeof t&&!!t.tag};e.isTagNode=n;var r=function(t){return"string"==typeof t};e.isStringNode=r;e.isEOL=function(t){return t===A.N};e.getNodeLength=function t(e){return n(e)?e.content.reduce((function(e,n){return e+t(n)}),0):r(e)?e.length:0};e.appendToNode=function(t,e){t.content.push(e)};var o=function(t){return t.replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/>/g,"&gt;").replace(/"/g,"&quot;").replace(/'/g,"&#039;").replace(/(javascript):/gi,"$1%3A")};e.escapeHTML=o;var i=function(t,e){var n=typeof e,r={boolean:function(){return e?""+t:""},number:function(){return t+'="'+e+'"'},string:function(){return t+'="'+o(e)+'"'},object:function(){return t+'="'+o(JSON.stringify(e))+'"'}};return r[n]?r[n]():""};e.attrValue=i;e.attrsToString=function(t){return void 0===t?"":Object.keys(t).reduce((function(e,n){return[].concat(e,[i(n,t[n])])}),[""]).join(" ")};e.getUniqAttr=function(t){return Object.keys(t).reduce((function(e,n){return t[n]===n?t[n]:null}),null)}}));e(T);var E=T.isTagNode,L=function(t){return t&&void 0!==t.value?t.value:""},S=function(t){return L(t).charCodeAt(0)===i.charCodeAt(0)},N=function(){function t(t,e,n,r){this.type=t+"",this.value=e+"",this.line=Number(n),this.row=Number(r)}var e=t.prototype;return e.isEmpty=function(){return!!this.type},e.isText=function(){return!(!(t=this)||void 0===t.type||"space"!==t.type&&"new-line"!==t.type&&"word"!==t.type);var t},e.isTag=function(){return!(!(t=this)||void 0===t.type)&&"tag"===t.type;var t},e.isAttrName=function(){return!(!(t=this)||void 0===t.type)&&"attr-name"===t.type;var t},e.isAttrValue=function(){return!(!(t=this)||void 0===t.type)&&"attr-value"===t.type;var t},e.isStart=function(){return!S(this)},e.isEnd=function(){return S(this)},e.getName=function(){return e=L(t=this),S(t)?e.slice(1):e;var t,e},e.getValue=function(){return L(this)},e.getLine=function(){return(t=this)&&t.line||0;var t},e.getColumn=function(){return(t=this)&&t.row||0;var t},e.toString=function(){return t=a,t+=L(this),t+=u;var t},t}(),y=function(t,e){var n={pos:0,length:t.length},r=function(){n.pos+=1,e&&e.onSkip&&e.onSkip()},o=function(){return n.length>n.pos},i=function(){return t.substr(n.pos)},u=function(){return t[n.pos]};return{skip:r,hasNext:o,isLast:function(){return n.pos===n.length},grabWhile:function(e){var i=0;if(o())for(i=n.pos;o()&&e(u());)r();return t.substr(i,n.pos-i)},getNext:function(){var e=n.pos+1;return e>t.length-1?null:t[e]},getPrev:function(){var e=n.pos-1;return void 0!==t[e]?t[e]:null},getCurr:u,getRest:i,substrUntilChar:function(t){var e=i(),n=e.indexOf(t);return 0>n?"":e.substr(0,n)}}},O=function(t){void 0===t&&(t=[]);var e=t;return{getLast:function(){return Array.isArray(e)&&e.length>0&&void 0!==e[e.length-1]?e[e.length-1]:null},flushLast:function(){return!!e.length&&e.pop()},push:function(t){return e.push(t)},toArray:function(){return e}}},b=function(t,e,n,r){return void 0===n&&(n=0),void 0===r&&(r=0),new N(t,e,n,r)};function C(t,e){void 0===e&&(e={});var n=0,r=0,p=-1,d=Array(Math.floor(t.length)),h=e.openTag||a,v=e.closeTag||u,A=e.enableEscapeTags,T=[v,h,c,o,s,l,f,g,"!"],E=[h,s,l,g],L=[s,l],S=[f,s,l],N=function(t){return L.indexOf(t)>=0},O=function(t){return-1===E.indexOf(t)},C=function(t){return t===h||t===v||t===o},_=function(t){return t===o},P=function(t){e.onToken&&e.onToken(t),d[p+=1]=t},R=function(t){for(var e=null,i=!1,u=[],a=y(t),s=function(t){var n=t===f,r=N(t),u=a.getPrev(),s=a.getNext(),l=u===o;return null===e?!1===(n||r||a.isLast()):!(!i||!function(t){return S.indexOf(t)>=0}(t))||!!(t!==c||l||(i=!i)||s===f||N(s))&&!1===(n||r)},l=function(){var t=a.grabWhile(s),i=a.getCurr();if(null===e)e=t;else if(N(i)||i===c||!a.hasNext()){var f=function(t){return t.replace(o+c,c)}(function(t,e){for(;t.charAt(0)===e;)t=t.substring(1);for(;t.charAt(t.length-1)===e;)t=t.substring(0,t.length-1);return t}(t,c));u.push(b("attr-value",f,n,r))}else u.push(b("attr-name",t,n,r));a.skip()};a.hasNext();)l();return{tag:e,attrs:u}},k=y(t,{onSkip:function(){r++}}),B=function(){var t=k.getCurr(),e=k.getNext();if(t===g)k.skip(),n++,P(b("new-line",t,n,r=0));else if(N(t)){var o=k.grabWhile(N);P(b("space",o,n,r))}else if(A&&_(t)&&C(e))k.skip(),k.skip(),P(b("word",e,n,r));else if(t===h){k.skip();var u=k.substrUntilChar(v),a=0===u.length||u.indexOf(h)>=0;if(T.indexOf(e)>=0||a||k.isLast())P(b("word",t,n,r));else{var s=k.grabWhile((function(t){return t!==v}));if(k.skip(),-1===s.indexOf(f)||s[0]===i)P(b("tag",s,n,r));else{var c=R(s);P(b("tag",c.tag,n,r)),c.attrs.map(P)}}}else if(t===v)k.skip(),P(b("word",t,n,r));else if(O(t))if(A&&_(t)&&!C(e))k.skip(),P(b("word",t,n,r));else{var l=k.grabWhile((function(t){return A?O(t)&&!_(t):O(t)}));P(b("word",l,n,r))}};return{tokenize:function(){for(;k.hasNext();)B();return d.length=p+1,d},isTokenNested:function(e){var n=h+i+e.getValue();return t.indexOf(n)>-1}}}var _=function(t,e){void 0===e&&(e={});var n=e,r=null,o=O(),i=O(),u=O(),a=O(),s={},c=function(){u.flushLast()&&a.flushLast()},f=function(t){var e,r,u=(e=i.getLast())&&Array.isArray(e.content)?e.content:o.toArray();Array.isArray(u)&&(E(t)?(r=t.tag,n.onlyAllowTags&&n.onlyAllowTags.length&&0>n.onlyAllowTags.indexOf(r)?u.push(""+t):u.push(t.toTagNode())):u.push(t))},l=function(t){c();var e=h.create(t.getValue()),n=function(t){return void 0===s[t.getValue()]&&(s[t.getValue()]=r.isTokenNested(t)),s[t.getValue()]}(t);u.push(e),n?i.push(e):f(e)},g=function(t){t.isStart()&&l(t),t.isEnd()&&function(t){c();var e=i.flushLast();if(e)f(e);else if("function"==typeof n.onError){var r=t.getValue(),o=t.getLine(),u=t.getColumn();n.onError({message:"Inconsistent tag '"+r+"' on line "+o+" and column "+u,tagName:r,lineNumber:o,columnNumber:u})}}(t)},p=function(t){var e=u.getLast(),n=t.getValue(),r=!!s[t];if(e)if(t.isAttrName())a.push(n),e.attr(a.getLast(),"");else if(t.isAttrValue()){var o=a.getLast();o?(e.attr(o,n),a.flushLast()):e.attr(n,n)}else t.isText()?r?e.append(n):f(n):t.isTag()&&f(""+t);else t.isText()?f(n):t.isTag()&&f(""+t)};(r=(e.createTokenizer?e.createTokenizer:C)(t,{onToken:function(t){t.isTag()?g(t):p(t)},onlyAllowTags:n.onlyAllowTags,openTag:n.openTag,closeTag:n.closeTag,enableEscapeTags:n.enableEscapeTags})).tokenize();return o.toArray()};t.TagNode=v,t.default=_,t.parse=_,Object.defineProperty(t,"__esModule",{value:!0})}));
!function(t,n){"object"==typeof exports&&"undefined"!=typeof module?n(exports):"function"==typeof define&&define.amd?define(["exports"],n):n((t=t||self).BbobParser={})}(this,(function(t){"use strict";function n(t){return t&&t.__esModule&&Object.prototype.hasOwnProperty.call(t,"default")?t.default:t}function e(t,n){return t(n={exports:{}},n.exports),n.exports}var r=e((function(t,n){n.__esModule=!0,n.BACKSLASH=n.PLACEHOLDER_SPACE=n.PLACEHOLDER_SPACE_TAB=n.SLASH=n.CLOSE_BRAKET=n.OPEN_BRAKET=n.SPACE=n.QUOTEMARK=n.EQ=n.TAB=n.R=n.F=n.N=void 0;n.N="\n";n.TAB="\t";n.F="\f";n.R="\r";n.EQ="=";n.QUOTEMARK='"';n.SPACE=" ";n.OPEN_BRAKET="[";n.CLOSE_BRAKET="]";n.SLASH="/";n.BACKSLASH="\\";n.PLACEHOLDER_SPACE_TAB=" ";n.PLACEHOLDER_SPACE=" "}));n(r);var i=r.BACKSLASH,u=r.SLASH,o=r.CLOSE_BRAKET,a=r.OPEN_BRAKET,s=r.SPACE,f=r.QUOTEMARK,c=r.EQ,l=r.TAB,g=r.N,p=e((function(t,n){n.__esModule=!0,n.isEOL=n.isStringNode=n.isTagNode=n.getUniqAttr=n.getNodeLength=n.escapeHTML=n.appendToNode=n.attrValue=n.attrsToString=void 0;var e=function(t){return"object"==typeof t&&!!t.tag};n.isTagNode=e;var i=function(t){return"string"==typeof t};n.isStringNode=i;n.isEOL=function(t){return t===r.N};var u=function(t,n,e){return Object.keys(t).reduce(n,e)};n.getNodeLength=function t(n){return e(n)?n.content.reduce((function(n,e){return n+t(e)}),0):i(n)?n.length:0};n.appendToNode=function(t,n){t.content.push(n)};var o=function(t){return t.replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/>/g,"&gt;").replace(/"/g,"&quot;").replace(/'/g,"&#039;").replace(/(javascript):/gi,"$1%3A")};n.escapeHTML=o;var a=function(t,n){var e=typeof n,r={boolean:function(){return n?""+t:""},number:function(){return t+'="'+n+'"'},string:function(){return t+'="'+o(n)+'"'},object:function(){return t+'="'+o(JSON.stringify(n))+'"'}};return r[e]?r[e]():""};n.attrValue=a;n.attrsToString=function(t){return null==t?"":u(t,(function(n,e){return[].concat(n,[a(e,t[e])])}),[""]).join(" ")};n.getUniqAttr=function(t){return u(t,(function(n,e){return t[e]===e?t[e]:null}),null)}}));n(p);var h=p.isTagNode,d=e((function(t,n){function e(t,n){for(var e=0;n.length>e;e++){var r=n[e];r.enumerable=r.enumerable||!1,r.configurable=!0,"value"in r&&(r.writable=!0),Object.defineProperty(t,r.key,r)}}function i(){return(i=Object.assign||function(t){for(var n=1;arguments.length>n;n++){var e=arguments[n];for(var r in e)Object.prototype.hasOwnProperty.call(e,r)&&(t[r]=e[r])}return t}).apply(this,arguments)}n.__esModule=!0,n.default=n.TagNode=void 0;var u=function(){function t(t,n,e){this.tag=t,this.attrs=n,this.content=Array.isArray(e)?e:[e]}var n,u,o,a=t.prototype;return a.attr=function(t,n){return void 0!==n&&(this.attrs[t]=n),this.attrs[t]},a.append=function(t){return(0,p.appendToNode)(this,t)},a.toTagNode=function(){return new t(this.tag.toLowerCase(),this.attrs,this.content)},a.toString=function(){var t=r.OPEN_BRAKET,n=r.CLOSE_BRAKET,e=0===this.content.length,u=this.content.reduce((function(t,n){return t+""+n}),""),o=function(t,n){var e=(0,p.getUniqAttr)(n);if(e){var r=(0,p.attrValue)(t,e),u=i({},n);return delete u[e],""+r+(0,p.attrsToString)(u)}return""+t+(0,p.attrsToString)(n)}(this.tag,this.attrs);return e?""+t+o+n:""+t+o+n+u+t+r.SLASH+this.tag+n},n=t,(u=[{key:"length",get:function(){return(0,p.getNodeLength)(this)}}])&&e(n.prototype,u),o&&e(n,o),t}();n.TagNode=u,u.create=function(t,n,e){return void 0===n&&(n={}),void 0===e&&(e=[]),new u(t,n,e)},u.isOf=function(t,n){return t.tag===n},n.default=u})),v=n(d),A=d.TagNode,T=function(t){return t&&void 0!==t.value?t.value:""},y=function(t){return T(t).charCodeAt(0)===u.charCodeAt(0)},E=function(){function t(t,n,e,r){this.type=Number(t),this.value=n+"",this.line=Number(e),this.row=Number(r)}var n=t.prototype;return n.isEmpty=function(){return isNaN(this.type)},n.isText=function(){return!(!(t=this)||void 0===t.type||5!==t.type&&6!==t.type&&1!==t.type);var t},n.isTag=function(){return!(!(t=this)||void 0===t.type)&&2===t.type;var t},n.isAttrName=function(){return!(!(t=this)||void 0===t.type)&&3===t.type;var t},n.isAttrValue=function(){return!(!(t=this)||void 0===t.type)&&4===t.type;var t},n.isStart=function(){return!y(this)},n.isEnd=function(){return y(this)},n.getName=function(){return n=T(t=this),y(t)?n.slice(1):n;var t,n},n.getValue=function(){return T(this)},n.getLine=function(){return(t=this)&&t.line||0;var t},n.getColumn=function(){return(t=this)&&t.row||0;var t},n.toString=function(){return t=a,t+=T(this),t+=o;var t},t}();function N(t,n){var e={pos:0,len:t.length},r=function(){return e.len>e.pos},i=function(t,r){void 0===t&&(t=1),e.pos+=t,n&&n.onSkip&&!r&&n.onSkip()},u=function(){return t[e.pos]};this.skip=i,this.hasNext=r,this.getCurr=u,this.getRest=function(){return t.substr(e.pos)},this.getNext=function(){var n=e.pos+1;return n>t.length-1?null:t[n]},this.getPrev=function(){var n=e.pos-1;return void 0!==t[n]?t[n]:null},this.isLast=function(){return e.pos===e.len},this.includes=function(n){return t.indexOf(n,e.pos)>=0},this.grabWhile=function(n,o){var a=0;if(r())for(a=e.pos;r()&&n(u());)i(1,o);return t.substr(a,e.pos-a)},this.substrUntilChar=function(n){var r=e.pos,i=t.indexOf(n,r);return 0>i?"":t.substr(r,i-r)}}var b=function(t,n){return new N(t,n)};function L(t){void 0===t&&(t=[]);var n=t;this.push=function(t){return n.push(t)},this.toArray=function(){return n},this.getLast=function(){return Array.isArray(n)&&n.length>0&&void 0!==n[n.length-1]?n[n.length-1]:null},this.flushLast=function(){return!!n.length&&n.pop()}}var S=function(t){return void 0===t&&(t=[]),new L(t)};function O(t,n){void 0===n&&(n={});var e=0,r=0,p=-1,h=0,d=0,v=Array(Math.floor(t.length)),A=n.openTag||a,T=n.closeTag||o,y=!!n.enableEscapeTags,N=n.onToken||function(){},L=[T,A,f,i,s,l,c,g,"!"],S=[A,s,l,g],O=[s,l],C=[c,s,l],k=function(t){return O.indexOf(t)>=0},x=function(t){return-1===S.indexOf(t)},_=function(t){return t===i},P=function(){r++},m=function(t){return function(t){return t.replace(i+f,f)}(function(t,n){for(;t.charAt(0)===n;)t=t.substring(1);for(;t.charAt(t.length-1)===n;)t=t.substring(0,t.length-1);return t}(t,f))},R=b(t,{onSkip:P});function w(t,n){var i=function(t,n,e,r){return void 0===e&&(e=0),void 0===r&&(r=0),new E(t,n,e,r)}(t,n,e,r);N(i),v[p+=1]=i}function B(t,n){if(1===d){var e=t.grabWhile((function(t){return!(t===c||k(t))})),r=t.isLast(),u=t.getCurr()!==c;return t.skip(),r||u?w(4,m(e)):w(3,e),r?0:u?1:2}if(2===d){var o=!1,a=t.grabWhile((function(e){var r=e===f,u=t.getPrev(),a=t.getNext(),s=u===i,l=a===c,g=k(e),p=k(a);return!(!o||!function(t){return C.indexOf(t)>=0}(e))||!!(!r||s||(o=!o)||l||p)&&(!!n||!1===g)}));return t.skip(),w(4,m(a)),t.isLast()?0:1}return w(2,t.grabWhile((function(n){return!(n===c||k(n)||t.isLast())}))),t.skip(),n?2:t.includes(c)?1:2}function K(){var t=R.getCurr();if(t===A){var n=R.getNext();R.skip();var e=R.substrUntilChar(T),r=0===e.length||e.indexOf(A)>=0;if(L.indexOf(n)>=0||r||R.isLast())return w(1,t),0;if(-1===e.indexOf(c)||e[0]===u){var i=R.grabWhile((function(t){return t!==T}));return R.skip(),w(2,i),0}return 2}return 0}function H(){for(var t=R.grabWhile((function(t){return t!==T}),!0),n=b(t,{onSkip:P}),e=n.includes(s);n.hasNext();)d=B(n,!e);return R.skip(),0}function V(){if(R.getCurr()===g)return w(6,R.getCurr()),R.skip(),r=0,e++,0;if(k(R.getCurr()))return w(5,R.grabWhile(k)),0;if(R.getCurr()===A)return R.includes(T)?1:(w(1,R.getCurr()),R.skip(),0);if(y){if(_(R.getCurr())){var t=R.getCurr(),n=R.getNext();return R.skip(),function(t){return t===A||t===T||t===i}(n)?(R.skip(),w(1,n),0):(w(1,t),0)}return w(1,R.grabWhile((function(t){return x(t)&&!_(t)}))),0}return w(1,R.grabWhile(x)),0}return{tokenize:function(){for(;R.hasNext();)switch(h){case 1:h=K();break;case 2:h=H();break;case 0:h=V();break;default:h=0}return v.length=p+1,v},isTokenNested:function(n){var e=A+u+n.getValue();return t.indexOf(e)>-1}}}var C=function(t,n){void 0===n&&(n={});var e=n,r=null,i=S(),u=S(),o=S(),a=S(),s={},f=function(){o.flushLast()&&a.flushLast()},c=function(t){var n,r,o=(n=u.getLast())&&Array.isArray(n.content)?n.content:i.toArray();Array.isArray(o)&&(h(t)?(r=t.tag,e.onlyAllowTags&&e.onlyAllowTags.length&&0>e.onlyAllowTags.indexOf(r)?o.push(""+t):o.push(t.toTagNode())):o.push(t))},l=function(t){f();var n=v.create(t.getValue()),e=function(t){return void 0===s[t.getValue()]&&(s[t.getValue()]=r.isTokenNested(t)),s[t.getValue()]}(t);o.push(n),e?u.push(n):c(n)},g=function(t){t.isStart()&&l(t),t.isEnd()&&function(t){f();var n=u.flushLast();if(n)c(n);else if("function"==typeof e.onError){var r=t.getValue(),i=t.getLine(),o=t.getColumn();e.onError({message:"Inconsistent tag '"+r+"' on line "+i+" and column "+o,tagName:r,lineNumber:i,columnNumber:o})}}(t)},p=function(t){var n=o.getLast(),e=t.getValue(),r=!!s[t];if(n)if(t.isAttrName())a.push(e),n.attr(a.getLast(),"");else if(t.isAttrValue()){var i=a.getLast();i?(n.attr(i,e),a.flushLast()):n.attr(e,e)}else t.isText()?r?n.append(e):c(e):t.isTag()&&c(""+t);else t.isText()?c(e):t.isTag()&&c(""+t)};(r=(n.createTokenizer?n.createTokenizer:O)(t,{onToken:function(t){t.isTag()?g(t):p(t)},onlyAllowTags:e.onlyAllowTags,openTag:e.openTag,closeTag:e.closeTag,enableEscapeTags:e.enableEscapeTags})).tokenize();return i.toArray()};t.TagNode=A,t.default=C,t.parse=C,Object.defineProperty(t,"__esModule",{value:!0})}));

327

es/lexer.js

@@ -18,3 +18,3 @@ "use strict";

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -58,9 +58,20 @@ * @param {Number} r line number

var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_TAG_ATTRS = 2;
var TAG_STATE_NAME = 0;
var TAG_STATE_ATTR = 1;
var TAG_STATE_VALUE = 2;
var row = 0;
var col = 0;
var tokenIndex = -1;
var stateMode = STATE_WORD;
var tagMode = TAG_STATE_NAME;
var tokens = new Array(Math.floor(buffer.length));
var openTag = options.openTag || _char.OPEN_BRAKET;
var closeTag = options.closeTag || _char.CLOSE_BRAKET;
var escapeTags = options.enableEscapeTags;
var escapeTags = !!options.enableEscapeTags;
var onToken = options.onToken || (() => {});
var RESERVED_CHARS = [closeTag, openTag, _char.QUOTEMARK, _char.BACKSLASH, _char.SPACE, _char.TAB, _char.EQ, _char.N, EM];

@@ -74,2 +85,4 @@ var NOT_CHAR_TOKENS = [// ...(options.enableEscapeTags ? [BACKSLASH] : []),

var isNewLine = char => char === _char.N;
var isWhiteSpace = char => WHITESPACES.indexOf(char) >= 0;

@@ -84,169 +97,245 @@

var isEscapeChar = char => char === _char.BACKSLASH;
var onSkip = () => {
col++;
};
var unq = val => (0, _utils.unquote)((0, _utils.trimChar)(val, _char.QUOTEMARK));
var chars = (0, _utils.createCharGrabber)(buffer, {
onSkip
});
/**
* Emits newly created token to subscriber
* @param token
* @param {Number} type
* @param {String} value
*/
var emitToken = token => {
if (options.onToken) {
options.onToken(token);
}
function emitToken(type, value) {
var token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
};
/**
* Parses params inside [myTag---params goes here---]content[/myTag]
* @param str
* @returns {{tag: *, attrs: Array}}
*/
}
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_ATTR) {
var validAttrName = char => !(char === _char.EQ || isWhiteSpace(char));
var parseAttrs = str => {
var tagName = null;
var skipSpecialChars = false;
var attrTokens = [];
var attrCharGrabber = (0, _utils.createCharGrabber)(str);
var _name = tagChars.grabWhile(validAttrName);
var validAttr = char => {
var isEQ = char === _char.EQ;
var isWS = isWhiteSpace(char);
var prevChar = attrCharGrabber.getPrev();
var nextChar = attrCharGrabber.getNext();
var isPrevSLASH = prevChar === _char.BACKSLASH;
var isTagNameEmpty = tagName === null;
var isEnd = tagChars.isLast();
if (isTagNameEmpty) {
return (isEQ || isWS || attrCharGrabber.isLast()) === false;
var isValue = tagChars.getCurr() !== _char.EQ;
tagChars.skip();
if (isEnd || isValue) {
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name));
} else {
emitToken(_Token.TYPE_ATTR_NAME, _name);
}
if (skipSpecialChars && isSpecialChar(char)) {
return true;
if (isEnd) {
return TAG_STATE_NAME;
}
if (char === _char.QUOTEMARK && !isPrevSLASH) {
skipSpecialChars = !skipSpecialChars;
if (isValue) {
return TAG_STATE_ATTR;
}
if (!skipSpecialChars && !(nextChar === _char.EQ || isWhiteSpace(nextChar))) {
return false;
return TAG_STATE_VALUE;
}
if (tagMode === TAG_STATE_VALUE) {
var stateSpecial = false;
var validAttrValue = char => {
// const isEQ = char === EQ;
var isQM = char === _char.QUOTEMARK;
var prevChar = tagChars.getPrev();
var nextChar = tagChars.getNext();
var isPrevSLASH = prevChar === _char.BACKSLASH;
var isNextEQ = nextChar === _char.EQ;
var isWS = isWhiteSpace(char); // const isPrevWS = isWhiteSpace(prevChar);
var isNextWS = isWhiteSpace(nextChar);
if (stateSpecial && isSpecialChar(char)) {
return true;
}
}
return (isEQ || isWS) === false;
};
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
var nextAttr = () => {
var attrStr = attrCharGrabber.grabWhile(validAttr);
var currChar = attrCharGrabber.getCurr(); // first string before space is a tag name [tagName params...]
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (tagName === null) {
tagName = attrStr;
} else if (isWhiteSpace(currChar) || currChar === _char.QUOTEMARK || !attrCharGrabber.hasNext()) {
var escaped = (0, _utils.unquote)((0, _utils.trimChar)(attrStr, _char.QUOTEMARK));
attrTokens.push(createToken(_Token.TYPE_ATTR_VALUE, escaped, row, col));
} else {
attrTokens.push(createToken(_Token.TYPE_ATTR_NAME, attrStr, row, col));
if (!isSingleValueTag) {
return isWS === false; // return (isEQ || isWS) === false;
}
return true;
};
var _name2 = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name2));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
attrCharGrabber.skip();
};
return TAG_STATE_ATTR;
}
while (attrCharGrabber.hasNext()) {
nextAttr();
var validName = char => !(char === _char.EQ || isWhiteSpace(char) || tagChars.isLast());
var name = tagChars.grabWhile(validName);
emitToken(_Token.TYPE_TAG, name);
tagChars.skip(); // in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
return {
tag: tagName,
attrs: attrTokens
};
};
var hasEQ = tagChars.includes(_char.EQ);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
var bufferGrabber = (0, _utils.createCharGrabber)(buffer, {
onSkip: () => {
col++;
function stateTag() {
var currChar = chars.getCurr();
if (currChar === openTag) {
var nextChar = chars.getNext();
chars.skip(); // detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var substr = chars.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
} // [myTag ]
var isNoAttrsInTag = substr.indexOf(_char.EQ) === -1; // [/myTag]
var isClosingTag = substr[0] === _char.SLASH;
if (isNoAttrsInTag || isClosingTag) {
var name = chars.grabWhile(char => char !== closeTag);
chars.skip(); // skip closeTag
emitToken(_Token.TYPE_TAG, name);
return STATE_WORD;
}
return STATE_TAG_ATTRS;
}
});
var next = () => {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
return STATE_WORD;
}
if (currChar === _char.N) {
bufferGrabber.skip();
function stateAttrs() {
var silent = true;
var tagStr = chars.grabWhile(char => char !== closeTag, silent);
var tagGrabber = (0, _utils.createCharGrabber)(tagStr, {
onSkip
});
var hasSpace = tagGrabber.includes(_char.SPACE);
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
chars.skip(); // skip closeTag
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(_Token.TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
emitToken(createToken(_Token.TYPE_NEW_LINE, currChar, row, col));
} else if (isWhiteSpace(currChar)) {
var str = bufferGrabber.grabWhile(isWhiteSpace);
emitToken(createToken(_Token.TYPE_SPACE, str, row, col));
} else if (escapeTags && isEscapeChar(currChar) && isEscapableChar(nextChar)) {
bufferGrabber.skip(); // skip the \ without emitting anything
return STATE_WORD;
}
bufferGrabber.skip(); // skip past the [, ] or \ as well
if (isWhiteSpace(chars.getCurr())) {
emitToken(_Token.TYPE_SPACE, chars.grabWhile(isWhiteSpace));
return STATE_WORD;
}
emitToken(createToken(_Token.TYPE_WORD, nextChar, row, col));
} else if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
var substr = bufferGrabber.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
emitToken(_Token.TYPE_WORD, chars.getCurr());
chars.skip();
return STATE_WORD;
}
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else {
var _str = bufferGrabber.grabWhile(val => val !== closeTag);
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
var currChar = chars.getCurr();
var nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
bufferGrabber.skip(); // skip closeTag
// [myTag ]
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
var isNoAttrsInTag = _str.indexOf(_char.EQ) === -1; // [/myTag]
emitToken(_Token.TYPE_WORD, nextChar);
return STATE_WORD;
}
var isClosingTag = _str[0] === _char.SLASH;
if (isNoAttrsInTag || isClosingTag) {
emitToken(createToken(_Token.TYPE_TAG, _str, row, col));
} else {
var parsed = parseAttrs(_str);
emitToken(createToken(_Token.TYPE_TAG, parsed.tag, row, col));
parsed.attrs.map(emitToken);
}
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
} else if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else if (isCharToken(currChar)) {
if (escapeTags && isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else {
var _str2 = bufferGrabber.grabWhile(char => {
if (escapeTags) {
return isCharToken(char) && !isEscapeChar(char);
}
var isChar = char => isCharToken(char) && !isEscapeChar(char);
return isCharToken(char);
});
emitToken(_Token.TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
emitToken(createToken(_Token.TYPE_WORD, _str2, row, col));
emitToken(_Token.TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
case STATE_WORD:
stateMode = stateWord();
break;
default:
stateMode = STATE_WORD;
break;
}
}
};
var tokenize = () => {
while (bufferGrabber.hasNext()) {
next();
}
tokens.length = tokenIndex + 1;
return tokens;
};
}
var isTokenNested = token => {
function isTokenNested(token) {
var value = openTag + _char.SLASH + token.getValue(); // potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -253,0 +342,0 @@ return {

310

es/lexer2.js

@@ -18,3 +18,3 @@ "use strict";

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -41,10 +41,3 @@ * @param {Number} r line number

*/
// [tag attr-name="attr-value"]content[/tag] other content
var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_ATTR = 2;
var STATE_ATTR_NAME = 3;
var STATE_ATTR_VALUE = 4;
/**

@@ -60,2 +53,3 @@ * @param {String} buffer

function createLexer(buffer, options) {

@@ -66,10 +60,20 @@ if (options === void 0) {

var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_TAG_ATTRS = 2;
var TAG_STATE_NAME = 0;
var TAG_STATE_ATTR = 1;
var TAG_STATE_VALUE = 2;
var row = 0;
var col = 0;
var tokenIndex = -1;
var mode = 0;
var stateMode = STATE_WORD;
var tagMode = TAG_STATE_NAME;
var tokens = new Array(Math.floor(buffer.length));
var openTag = options.openTag || _char.OPEN_BRAKET;
var closeTag = options.closeTag || _char.CLOSE_BRAKET;
var escapeTags = options.enableEscapeTags;
var escapeTags = !!options.enableEscapeTags;
var onToken = options.onToken || (() => {});
var RESERVED_CHARS = [closeTag, openTag, _char.QUOTEMARK, _char.BACKSLASH, _char.SPACE, _char.TAB, _char.EQ, _char.N, EM];

@@ -95,121 +99,263 @@ var NOT_CHAR_TOKENS = [// ...(options.enableEscapeTags ? [BACKSLASH] : []),

var bufferGrabber = (0, _utils.createCharGrabber)(buffer, {
onSkip: () => {
col++;
}
var onSkip = () => {
col++;
};
var unq = val => (0, _utils.unquote)((0, _utils.trimChar)(val, _char.QUOTEMARK));
var chars = (0, _utils.createCharGrabber)(buffer, {
onSkip
});
/**
* Emits newly created token to subscriber
* @param token
* @param {Number} type
* @param {String} value
*/
var emitToken = token => {
if (options.onToken) {
options.onToken(token);
}
function emitToken(type, value) {
var token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
};
}
var switchMode = newMode => {
mode = newMode;
};
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_NAME) {
var currChar = tagChars.getCurr();
var hasNext = tagChars.hasNext();
var isWS = isWhiteSpace(currChar);
var isQM = currChar === _char.QUOTEMARK;
var processWord = () => {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
if (isWS || isQM || !hasNext) {
return TAG_STATE_VALUE;
}
if (currChar === openTag && bufferGrabber.includes(closeTag)) {
return switchMode(STATE_TAG);
}
var validName = char => !(char === _char.EQ || isWhiteSpace(char) || tagChars.isLast());
if (isNewLine(currChar)) {
bufferGrabber.skip();
col = 0;
row++;
return emitToken(createToken(_Token.TYPE_NEW_LINE, currChar, row, col));
}
var name = tagChars.grabWhile(validName);
emitToken(_Token.TYPE_TAG, name);
tagChars.skip(); // in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isWhiteSpace(currChar)) {
return emitToken(createToken(_Token.TYPE_SPACE, bufferGrabber.grabWhile(isWhiteSpace), row, col));
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
var hasEQ = tagChars.includes(_char.EQ);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
if (escapeTags) {
if (isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
if (tagMode === TAG_STATE_ATTR) {
var validAttrName = char => !(char === _char.EQ || isWhiteSpace(char));
var _name = tagChars.grabWhile(validAttrName);
var isEnd = tagChars.isLast();
var isValue = tagChars.getCurr() !== _char.EQ;
tagChars.skip();
if (isEnd || isValue) {
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name));
} else {
emitToken(_Token.TYPE_ATTR_NAME, _name);
}
var _str = bufferGrabber.grabWhile(char => isCharToken(char) && !isEscapeChar(char));
if (isEnd) {
return TAG_STATE_NAME;
}
return emitToken(createToken(_Token.TYPE_WORD, _str, row, col));
if (isValue) {
return TAG_STATE_ATTR;
}
return TAG_STATE_VALUE;
}
var str = bufferGrabber.grabWhile(char => isCharToken(char));
return emitToken(createToken(_Token.TYPE_WORD, str, row, col));
};
if (tagMode === TAG_STATE_VALUE) {
var stateSpecial = false;
var processTag = () => {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
var validAttrValue = char => {
// const isEQ = char === EQ;
var isQM = char === _char.QUOTEMARK;
var prevChar = tagChars.getPrev();
var nextChar = tagChars.getNext();
var isPrevSLASH = prevChar === _char.BACKSLASH;
var isNextEQ = nextChar === _char.EQ;
var isWS = isWhiteSpace(char); // const isPrevWS = isWhiteSpace(prevChar);
if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
var isNextWS = isWhiteSpace(nextChar);
switchMode(STATE_WORD);
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
if (stateSpecial && isSpecialChar(char)) {
return true;
}
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (!isSingleValueTag) {
return isWS === false; // return (isEQ || isWS) === false;
}
return true;
};
var _name2 = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name2));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
return TAG_STATE_ATTR;
}
return TAG_STATE_NAME;
}
function stateTag() {
var currChar = chars.getCurr();
if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var nextChar = chars.getNext();
chars.skip(); // detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var str = bufferGrabber.grabWhile(val => val !== closeTag);
var hasInvalidChars = str.length === 0 || str.indexOf(openTag) >= 0;
var substr = chars.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
}
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
} // [myTag ]
bufferGrabber.skip(); // skip closeTag
// [myTag ]
var isNoAttrsInTag = str.indexOf(_char.EQ) === -1; // [/myTag]
var isNoAttrsInTag = substr.indexOf(_char.EQ) === -1; // [/myTag]
var isClosingTag = str[0] === _char.SLASH;
var isClosingTag = substr[0] === _char.SLASH;
if (isNoAttrsInTag || isClosingTag) {
return emitToken(createToken(_Token.TYPE_TAG, str, row, col));
var name = chars.grabWhile(char => char !== closeTag);
chars.skip(); // skip closeTag
emitToken(_Token.TYPE_TAG, name);
return STATE_WORD;
}
return STATE_TAG_ATTRS;
}
return switchMode(STATE_WORD);
};
if (currChar === closeTag) {
chars.skip();
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
var processAttrName = () => {};
return STATE_WORD;
}
var processAttrValue = () => {};
function stateAttrs() {
var silent = true;
var tagStr = chars.grabWhile(char => char !== closeTag, silent);
var tagGrabber = (0, _utils.createCharGrabber)(tagStr, {
onSkip
});
var hasSpace = tagGrabber.includes(_char.SPACE);
var modeMap = {
[STATE_WORD]: processWord,
[STATE_TAG]: processTag,
[STATE_ATTR_NAME]: processAttrName,
[STATE_ATTR_VALUE]: processAttrValue
};
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
var tokenize = () => {
while (bufferGrabber.hasNext()) {
modeMap[mode](bufferGrabber);
chars.skip(); // skip closeTag
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(_Token.TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
return STATE_WORD;
}
if (isWhiteSpace(chars.getCurr())) {
emitToken(_Token.TYPE_SPACE, chars.grabWhile(isWhiteSpace));
return STATE_WORD;
}
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
emitToken(_Token.TYPE_WORD, chars.getCurr());
chars.skip();
return STATE_WORD;
}
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
var currChar = chars.getCurr();
var nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
emitToken(_Token.TYPE_WORD, nextChar);
return STATE_WORD;
}
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
var isChar = char => isCharToken(char) && !isEscapeChar(char);
emitToken(_Token.TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
emitToken(_Token.TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
case STATE_WORD:
stateMode = stateWord();
break;
default:
stateMode = STATE_WORD;
break;
}
}
tokens.length = tokenIndex + 1;
return tokens;
};
}
var isTokenNested = token => {
function isTokenNested(token) {
var value = openTag + _char.SLASH + token.getValue(); // potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -216,0 +362,0 @@ return {

12

es/parse.js

@@ -8,3 +8,3 @@ "use strict";

var _pluginHelper = require("@bbob/plugin-helper");
var _index = require("@bbob/plugin-helper/lib/index");

@@ -38,3 +38,3 @@ var _lexer = require("./lexer");

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -46,3 +46,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -54,3 +54,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -62,3 +62,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -139,3 +139,3 @@

if (Array.isArray(items)) {
if ((0, _pluginHelper.isTagNode)(node)) {
if ((0, _index.isTagNode)(node)) {
if (isAllowedTag(node.tag)) {

@@ -142,0 +142,0 @@ items.push(node.toTagNode());

23

es/Token.js

@@ -17,8 +17,14 @@ "use strict";

var TOKEN_TYPE_WORD = 'word';
var TOKEN_TYPE_TAG = 'tag';
var TOKEN_TYPE_ATTR_NAME = 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 'attr-value';
var TOKEN_TYPE_SPACE = 'space';
var TOKEN_TYPE_NEW_LINE = 'new-line';
var TOKEN_TYPE_WORD = 1; // 'word';
var TOKEN_TYPE_TAG = 2; // 'tag';
var TOKEN_TYPE_ATTR_NAME = 3; // 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 4; // 'attr-value';
var TOKEN_TYPE_SPACE = 5; // 'space';
var TOKEN_TYPE_NEW_LINE = 6; // 'new-line';
/**

@@ -117,3 +123,3 @@ * @param {Token} token

constructor(type, value, line, row) {
this[TOKEN_TYPE_ID] = String(type);
this[TOKEN_TYPE_ID] = Number(type);
this[TOKEN_VALUE_ID] = String(value);

@@ -125,3 +131,4 @@ this[TOKEN_LINE_ID] = Number(line);

isEmpty() {
return !!this[TOKEN_TYPE_ID];
// eslint-disable-next-line no-restricted-globals
return isNaN(this[TOKEN_TYPE_ID]);
}

@@ -128,0 +135,0 @@

244

es/utils.js

@@ -8,28 +8,30 @@ "use strict";

/**
* @typedef {Object} CharGrabber
* @property {Function} skip
* @property {Function} hasNext
* @property {Function} isLast
* @property {Function} grabWhile
*/
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @returns
*/
var createCharGrabber = (source, options) => {
// let idx = 0;
function CharGrabber(source, options) {
var cursor = {
pos: 0,
length: source.length
len: source.length
};
var skip = () => {
cursor.pos += 1;
var substrUntilChar = char => {
var {
pos
} = cursor;
var idx = source.indexOf(char, pos);
return idx >= 0 ? source.substr(pos, idx - pos) : '';
};
if (options && options.onSkip) {
var includes = val => source.indexOf(val, cursor.pos) >= 0;
var hasNext = () => cursor.len > cursor.pos;
var isLast = () => cursor.pos === cursor.len;
var skip = function skip(num, silent) {
if (num === void 0) {
num = 1;
}
cursor.pos += num;
if (options && options.onSkip && !silent) {
options.onSkip();

@@ -39,69 +41,96 @@ }

var hasNext = () => cursor.length > cursor.pos;
var rest = () => source.substr(cursor.pos);
var getRest = () => source.substr(cursor.pos);
var curr = () => source[cursor.pos];
var getCurr = () => source[cursor.pos];
var prev = () => {
var prevPos = cursor.pos - 1;
return typeof source[prevPos] !== 'undefined' ? source[prevPos] : null;
};
return {
skip,
hasNext,
isLast: () => cursor.pos === cursor.length,
var next = () => {
var nextPos = cursor.pos + 1;
return nextPos <= source.length - 1 ? source[nextPos] : null;
};
/**
* @param {Function} cond
* @returns {string}
*/
grabWhile: cond => {
var start = 0;
var grabWhile = (cond, silent) => {
var start = 0;
if (hasNext()) {
start = cursor.pos;
if (hasNext()) {
start = cursor.pos;
while (hasNext() && cond(getCurr())) {
skip();
}
while (hasNext() && cond(curr())) {
skip(1, silent);
}
}
return source.substr(start, cursor.pos - start);
},
getNext: () => {
var nextPos = cursor.pos + 1;
return source.substr(start, cursor.pos - start);
};
/**
* @type {skip}
*/
if (nextPos <= source.length - 1) {
return source[nextPos];
}
return null;
},
getPrev: () => {
var prevPos = cursor.pos - 1;
this.skip = skip;
/**
* @returns {Boolean}
*/
if (typeof source[prevPos] !== 'undefined') {
return source[prevPos];
}
this.hasNext = hasNext;
/**
* @returns {String}
*/
return null;
},
getCurr,
getRest,
this.getCurr = curr;
/**
* @returns {String}
*/
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
substrUntilChar: char => {
var restStr = getRest();
var indexOfChar = restStr.indexOf(char);
this.getRest = rest;
/**
* @returns {String}
*/
if (indexOfChar >= 0) {
return restStr.substr(0, indexOfChar);
}
this.getNext = next;
/**
* @returns {String}
*/
return '';
}
};
};
this.getPrev = prev;
/**
* @returns {Boolean}
*/
this.isLast = isLast;
/**
* @returns {Boolean}
*/
this.includes = includes;
/**
* @param {Function} cond
* @param {Boolean} silent
* @return {String}
*/
this.grabWhile = grabWhile;
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
this.substrUntilChar = substrUntilChar;
}
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @return CharGrabber
*/
var createCharGrabber = (source, options) => new CharGrabber(source, options);
/**
* Trims string from start and end by char

@@ -141,21 +170,6 @@ * @example

var unquote = str => str.replace(_char.BACKSLASH + _char.QUOTEMARK, _char.QUOTEMARK);
/**
* @typedef {Object} ItemList
* @type {Object}
* @property {getLastCb} getLast
* @property {flushLastCb} flushLast
* @property {pushCb} push
* @property {toArrayCb} toArray
*/
/**
*
* @param values
* @return {ItemList}
*/
exports.unquote = unquote;
var createList = function createList(values) {
function NodeList(values) {
if (values === void 0) {

@@ -166,47 +180,31 @@ values = [];

var nodes = values;
/**
* @callback getLastCb
*/
var getLast = () => {
if (Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined') {
return nodes[nodes.length - 1];
}
var getLast = () => Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined' ? nodes[nodes.length - 1] : null;
return null;
};
/**
* @callback flushLastCb
* @return {*}
*/
var flushLast = () => nodes.length ? nodes.pop() : false;
var push = value => nodes.push(value);
var flushLast = () => {
if (nodes.length) {
return nodes.pop();
}
var toArray = () => nodes;
return false;
};
/**
* @callback pushCb
* @param value
*/
this.push = push;
this.toArray = toArray;
this.getLast = getLast;
this.flushLast = flushLast;
}
/**
*
* @param values
* @return {NodeList}
*/
var push = value => nodes.push(value);
/**
* @callback toArrayCb
* @return {Array}
*/
var createList = function createList(values) {
if (values === void 0) {
values = [];
}
return {
getLast,
flushLast,
push,
toArray: () => nodes
};
return new NodeList(values);
};
exports.createList = createList;

375

lib/lexer.js

@@ -7,3 +7,3 @@ "use strict";

var _char9 = require("@bbob/plugin-helper/lib/char");
var _char14 = require("@bbob/plugin-helper/lib/char");

@@ -19,3 +19,3 @@ var _Token = require("./Token");

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -59,14 +59,25 @@ * @param {Number} r line number

var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_TAG_ATTRS = 2;
var TAG_STATE_NAME = 0;
var TAG_STATE_ATTR = 1;
var TAG_STATE_VALUE = 2;
var row = 0;
var col = 0;
var tokenIndex = -1;
var stateMode = STATE_WORD;
var tagMode = TAG_STATE_NAME;
var tokens = new Array(Math.floor(buffer.length));
var openTag = options.openTag || _char9.OPEN_BRAKET;
var closeTag = options.closeTag || _char9.CLOSE_BRAKET;
var escapeTags = options.enableEscapeTags;
var RESERVED_CHARS = [closeTag, openTag, _char9.QUOTEMARK, _char9.BACKSLASH, _char9.SPACE, _char9.TAB, _char9.EQ, _char9.N, EM];
var openTag = options.openTag || _char14.OPEN_BRAKET;
var closeTag = options.closeTag || _char14.CLOSE_BRAKET;
var escapeTags = !!options.enableEscapeTags;
var onToken = options.onToken || function () {};
var RESERVED_CHARS = [closeTag, openTag, _char14.QUOTEMARK, _char14.BACKSLASH, _char14.SPACE, _char14.TAB, _char14.EQ, _char14.N, EM];
var NOT_CHAR_TOKENS = [// ...(options.enableEscapeTags ? [BACKSLASH] : []),
openTag, _char9.SPACE, _char9.TAB, _char9.N];
var WHITESPACES = [_char9.SPACE, _char9.TAB];
var SPECIAL_CHARS = [_char9.EQ, _char9.SPACE, _char9.TAB];
openTag, _char14.SPACE, _char14.TAB, _char14.N];
var WHITESPACES = [_char14.SPACE, _char14.TAB];
var SPECIAL_CHARS = [_char14.EQ, _char14.SPACE, _char14.TAB];

@@ -77,179 +88,269 @@ var isCharReserved = function isCharReserved(_char) {

var isWhiteSpace = function isWhiteSpace(_char2) {
return WHITESPACES.indexOf(_char2) >= 0;
var isNewLine = function isNewLine(_char2) {
return _char2 === _char14.N;
};
var isCharToken = function isCharToken(_char3) {
return NOT_CHAR_TOKENS.indexOf(_char3) === -1;
var isWhiteSpace = function isWhiteSpace(_char3) {
return WHITESPACES.indexOf(_char3) >= 0;
};
var isSpecialChar = function isSpecialChar(_char4) {
return SPECIAL_CHARS.indexOf(_char4) >= 0;
var isCharToken = function isCharToken(_char4) {
return NOT_CHAR_TOKENS.indexOf(_char4) === -1;
};
var isEscapableChar = function isEscapableChar(_char5) {
return _char5 === openTag || _char5 === closeTag || _char5 === _char9.BACKSLASH;
var isSpecialChar = function isSpecialChar(_char5) {
return SPECIAL_CHARS.indexOf(_char5) >= 0;
};
var isEscapeChar = function isEscapeChar(_char6) {
return _char6 === _char9.BACKSLASH;
var isEscapableChar = function isEscapableChar(_char6) {
return _char6 === openTag || _char6 === closeTag || _char6 === _char14.BACKSLASH;
};
/**
* Emits newly created token to subscriber
* @param token
*/
var isEscapeChar = function isEscapeChar(_char7) {
return _char7 === _char14.BACKSLASH;
};
var emitToken = function emitToken(token) {
if (options.onToken) {
options.onToken(token);
}
var onSkip = function onSkip() {
col++;
};
tokenIndex += 1;
tokens[tokenIndex] = token;
var unq = function unq(val) {
return (0, _utils.unquote)((0, _utils.trimChar)(val, _char14.QUOTEMARK));
};
var chars = (0, _utils.createCharGrabber)(buffer, {
onSkip: onSkip
});
/**
* Parses params inside [myTag---params goes here---]content[/myTag]
* @param str
* @returns {{tag: *, attrs: Array}}
* Emits newly created token to subscriber
* @param {Number} type
* @param {String} value
*/
function emitToken(type, value) {
var token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
}
var parseAttrs = function parseAttrs(str) {
var tagName = null;
var skipSpecialChars = false;
var attrTokens = [];
var attrCharGrabber = (0, _utils.createCharGrabber)(str);
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_ATTR) {
var validAttrName = function validAttrName(_char8) {
return !(_char8 === _char14.EQ || isWhiteSpace(_char8));
};
var validAttr = function validAttr(_char7) {
var isEQ = _char7 === _char9.EQ;
var isWS = isWhiteSpace(_char7);
var prevChar = attrCharGrabber.getPrev();
var nextChar = attrCharGrabber.getNext();
var isPrevSLASH = prevChar === _char9.BACKSLASH;
var isTagNameEmpty = tagName === null;
var _name = tagChars.grabWhile(validAttrName);
if (isTagNameEmpty) {
return (isEQ || isWS || attrCharGrabber.isLast()) === false;
var isEnd = tagChars.isLast();
var isValue = tagChars.getCurr() !== _char14.EQ;
tagChars.skip();
if (isEnd || isValue) {
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name));
} else {
emitToken(_Token.TYPE_ATTR_NAME, _name);
}
if (skipSpecialChars && isSpecialChar(_char7)) {
return true;
if (isEnd) {
return TAG_STATE_NAME;
}
if (_char7 === _char9.QUOTEMARK && !isPrevSLASH) {
skipSpecialChars = !skipSpecialChars;
if (isValue) {
return TAG_STATE_ATTR;
}
if (!skipSpecialChars && !(nextChar === _char9.EQ || isWhiteSpace(nextChar))) {
return false;
return TAG_STATE_VALUE;
}
if (tagMode === TAG_STATE_VALUE) {
var stateSpecial = false;
var validAttrValue = function validAttrValue(_char9) {
// const isEQ = char === EQ;
var isQM = _char9 === _char14.QUOTEMARK;
var prevChar = tagChars.getPrev();
var nextChar = tagChars.getNext();
var isPrevSLASH = prevChar === _char14.BACKSLASH;
var isNextEQ = nextChar === _char14.EQ;
var isWS = isWhiteSpace(_char9); // const isPrevWS = isWhiteSpace(prevChar);
var isNextWS = isWhiteSpace(nextChar);
if (stateSpecial && isSpecialChar(_char9)) {
return true;
}
}
return (isEQ || isWS) === false;
};
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
var nextAttr = function nextAttr() {
var attrStr = attrCharGrabber.grabWhile(validAttr);
var currChar = attrCharGrabber.getCurr(); // first string before space is a tag name [tagName params...]
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (tagName === null) {
tagName = attrStr;
} else if (isWhiteSpace(currChar) || currChar === _char9.QUOTEMARK || !attrCharGrabber.hasNext()) {
var escaped = (0, _utils.unquote)((0, _utils.trimChar)(attrStr, _char9.QUOTEMARK));
attrTokens.push(createToken(_Token.TYPE_ATTR_VALUE, escaped, row, col));
} else {
attrTokens.push(createToken(_Token.TYPE_ATTR_NAME, attrStr, row, col));
if (!isSingleValueTag) {
return isWS === false; // return (isEQ || isWS) === false;
}
return true;
};
var _name2 = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name2));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
attrCharGrabber.skip();
};
while (attrCharGrabber.hasNext()) {
nextAttr();
return TAG_STATE_ATTR;
}
return {
tag: tagName,
attrs: attrTokens
var validName = function validName(_char10) {
return !(_char10 === _char14.EQ || isWhiteSpace(_char10) || tagChars.isLast());
};
};
var bufferGrabber = (0, _utils.createCharGrabber)(buffer, {
onSkip: function onSkip() {
col++;
var name = tagChars.grabWhile(validName);
emitToken(_Token.TYPE_TAG, name);
tagChars.skip(); // in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
});
var next = function next() {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
var hasEQ = tagChars.includes(_char14.EQ);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
if (currChar === _char9.N) {
bufferGrabber.skip();
col = 0;
row++;
emitToken(createToken(_Token.TYPE_NEW_LINE, currChar, row, col));
} else if (isWhiteSpace(currChar)) {
var str = bufferGrabber.grabWhile(isWhiteSpace);
emitToken(createToken(_Token.TYPE_SPACE, str, row, col));
} else if (escapeTags && isEscapeChar(currChar) && isEscapableChar(nextChar)) {
bufferGrabber.skip(); // skip the \ without emitting anything
function stateTag() {
var currChar = chars.getCurr();
bufferGrabber.skip(); // skip past the [, ] or \ as well
if (currChar === openTag) {
var nextChar = chars.getNext();
chars.skip(); // detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
emitToken(createToken(_Token.TYPE_WORD, nextChar, row, col));
} else if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var substr = bufferGrabber.substrUntilChar(closeTag);
var substr = chars.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else {
var _str = bufferGrabber.grabWhile(function (val) {
return val !== closeTag;
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
} // [myTag ]
var isNoAttrsInTag = substr.indexOf(_char14.EQ) === -1; // [/myTag]
var isClosingTag = substr[0] === _char14.SLASH;
if (isNoAttrsInTag || isClosingTag) {
var name = chars.grabWhile(function (_char11) {
return _char11 !== closeTag;
});
chars.skip(); // skip closeTag
bufferGrabber.skip(); // skip closeTag
// [myTag ]
emitToken(_Token.TYPE_TAG, name);
return STATE_WORD;
}
var isNoAttrsInTag = _str.indexOf(_char9.EQ) === -1; // [/myTag]
return STATE_TAG_ATTRS;
}
var isClosingTag = _str[0] === _char9.SLASH;
return STATE_WORD;
}
if (isNoAttrsInTag || isClosingTag) {
emitToken(createToken(_Token.TYPE_TAG, _str, row, col));
} else {
var parsed = parseAttrs(_str);
emitToken(createToken(_Token.TYPE_TAG, parsed.tag, row, col));
parsed.attrs.map(emitToken);
}
function stateAttrs() {
var silent = true;
var tagStr = chars.grabWhile(function (_char12) {
return _char12 !== closeTag;
}, silent);
var tagGrabber = (0, _utils.createCharGrabber)(tagStr, {
onSkip: onSkip
});
var hasSpace = tagGrabber.includes(_char14.SPACE);
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
chars.skip(); // skip closeTag
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(_Token.TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
return STATE_WORD;
}
if (isWhiteSpace(chars.getCurr())) {
emitToken(_Token.TYPE_SPACE, chars.grabWhile(isWhiteSpace));
return STATE_WORD;
}
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
} else if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else if (isCharToken(currChar)) {
if (escapeTags && isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
} else {
var _str2 = bufferGrabber.grabWhile(function (_char8) {
if (escapeTags) {
return isCharToken(_char8) && !isEscapeChar(_char8);
}
emitToken(_Token.TYPE_WORD, chars.getCurr());
chars.skip();
return STATE_WORD;
}
return isCharToken(_char8);
});
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
var currChar = chars.getCurr();
var nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
emitToken(createToken(_Token.TYPE_WORD, _str2, row, col));
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
emitToken(_Token.TYPE_WORD, nextChar);
return STATE_WORD;
}
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
var isChar = function isChar(_char13) {
return isCharToken(_char13) && !isEscapeChar(_char13);
};
emitToken(_Token.TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
};
var tokenize = function tokenize() {
while (bufferGrabber.hasNext()) {
next();
emitToken(_Token.TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
case STATE_WORD:
stateMode = stateWord();
break;
default:
stateMode = STATE_WORD;
break;
}
}

@@ -259,9 +360,9 @@

return tokens;
};
}
var isTokenNested = function isTokenNested(token) {
var value = openTag + _char9.SLASH + token.getValue(); // potential bottleneck
function isTokenNested(token) {
var value = openTag + _char14.SLASH + token.getValue(); // potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -268,0 +369,0 @@ return {

345

lib/lexer2.js

@@ -7,3 +7,3 @@ "use strict";

var _char10 = require("@bbob/plugin-helper/lib/char");
var _char14 = require("@bbob/plugin-helper/lib/char");

@@ -19,3 +19,3 @@ var _Token = require("./Token");

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -42,10 +42,3 @@ * @param {Number} r line number

*/
// [tag attr-name="attr-value"]content[/tag] other content
var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_ATTR = 2;
var STATE_ATTR_NAME = 3;
var STATE_ATTR_VALUE = 4;
/**

@@ -61,5 +54,4 @@ * @param {String} buffer

function createLexer(buffer, options) {
var _modeMap;
if (options === void 0) {

@@ -69,15 +61,25 @@ options = {};

var STATE_WORD = 0;
var STATE_TAG = 1;
var STATE_TAG_ATTRS = 2;
var TAG_STATE_NAME = 0;
var TAG_STATE_ATTR = 1;
var TAG_STATE_VALUE = 2;
var row = 0;
var col = 0;
var tokenIndex = -1;
var mode = 0;
var stateMode = STATE_WORD;
var tagMode = TAG_STATE_NAME;
var tokens = new Array(Math.floor(buffer.length));
var openTag = options.openTag || _char10.OPEN_BRAKET;
var closeTag = options.closeTag || _char10.CLOSE_BRAKET;
var escapeTags = options.enableEscapeTags;
var RESERVED_CHARS = [closeTag, openTag, _char10.QUOTEMARK, _char10.BACKSLASH, _char10.SPACE, _char10.TAB, _char10.EQ, _char10.N, EM];
var openTag = options.openTag || _char14.OPEN_BRAKET;
var closeTag = options.closeTag || _char14.CLOSE_BRAKET;
var escapeTags = !!options.enableEscapeTags;
var onToken = options.onToken || function () {};
var RESERVED_CHARS = [closeTag, openTag, _char14.QUOTEMARK, _char14.BACKSLASH, _char14.SPACE, _char14.TAB, _char14.EQ, _char14.N, EM];
var NOT_CHAR_TOKENS = [// ...(options.enableEscapeTags ? [BACKSLASH] : []),
openTag, _char10.SPACE, _char10.TAB, _char10.N];
var WHITESPACES = [_char10.SPACE, _char10.TAB];
var SPECIAL_CHARS = [_char10.EQ, _char10.SPACE, _char10.TAB];
openTag, _char14.SPACE, _char14.TAB, _char14.N];
var WHITESPACES = [_char14.SPACE, _char14.TAB];
var SPECIAL_CHARS = [_char14.EQ, _char14.SPACE, _char14.TAB];

@@ -89,3 +91,3 @@ var isCharReserved = function isCharReserved(_char) {

var isNewLine = function isNewLine(_char2) {
return _char2 === _char10.N;
return _char2 === _char14.N;
};

@@ -106,118 +108,271 @@

var isEscapableChar = function isEscapableChar(_char6) {
return _char6 === openTag || _char6 === closeTag || _char6 === _char10.BACKSLASH;
return _char6 === openTag || _char6 === closeTag || _char6 === _char14.BACKSLASH;
};
var isEscapeChar = function isEscapeChar(_char7) {
return _char7 === _char10.BACKSLASH;
return _char7 === _char14.BACKSLASH;
};
var bufferGrabber = (0, _utils.createCharGrabber)(buffer, {
onSkip: function onSkip() {
col++;
}
var onSkip = function onSkip() {
col++;
};
var unq = function unq(val) {
return (0, _utils.unquote)((0, _utils.trimChar)(val, _char14.QUOTEMARK));
};
var chars = (0, _utils.createCharGrabber)(buffer, {
onSkip: onSkip
});
/**
* Emits newly created token to subscriber
* @param token
* @param {Number} type
* @param {String} value
*/
var emitToken = function emitToken(token) {
if (options.onToken) {
options.onToken(token);
}
function emitToken(type, value) {
var token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
};
}
var switchMode = function switchMode(newMode) {
mode = newMode;
};
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_NAME) {
var currChar = tagChars.getCurr();
var hasNext = tagChars.hasNext();
var isWS = isWhiteSpace(currChar);
var isQM = currChar === _char14.QUOTEMARK;
var processWord = function processWord() {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
if (isWS || isQM || !hasNext) {
return TAG_STATE_VALUE;
}
if (currChar === openTag && bufferGrabber.includes(closeTag)) {
return switchMode(STATE_TAG);
var validName = function validName(_char8) {
return !(_char8 === _char14.EQ || isWhiteSpace(_char8) || tagChars.isLast());
};
var name = tagChars.grabWhile(validName);
emitToken(_Token.TYPE_TAG, name);
tagChars.skip(); // in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
var hasEQ = tagChars.includes(_char14.EQ);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
if (isNewLine(currChar)) {
bufferGrabber.skip();
col = 0;
row++;
return emitToken(createToken(_Token.TYPE_NEW_LINE, currChar, row, col));
if (tagMode === TAG_STATE_ATTR) {
var validAttrName = function validAttrName(_char9) {
return !(_char9 === _char14.EQ || isWhiteSpace(_char9));
};
var _name = tagChars.grabWhile(validAttrName);
var isEnd = tagChars.isLast();
var isValue = tagChars.getCurr() !== _char14.EQ;
tagChars.skip();
if (isEnd || isValue) {
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name));
} else {
emitToken(_Token.TYPE_ATTR_NAME, _name);
}
if (isEnd) {
return TAG_STATE_NAME;
}
if (isValue) {
return TAG_STATE_ATTR;
}
return TAG_STATE_VALUE;
}
if (isWhiteSpace(currChar)) {
return emitToken(createToken(_Token.TYPE_SPACE, bufferGrabber.grabWhile(isWhiteSpace), row, col));
if (tagMode === TAG_STATE_VALUE) {
var stateSpecial = false;
var validAttrValue = function validAttrValue(_char10) {
// const isEQ = char === EQ;
var isQM = _char10 === _char14.QUOTEMARK;
var prevChar = tagChars.getPrev();
var nextChar = tagChars.getNext();
var isPrevSLASH = prevChar === _char14.BACKSLASH;
var isNextEQ = nextChar === _char14.EQ;
var isWS = isWhiteSpace(_char10); // const isPrevWS = isWhiteSpace(prevChar);
var isNextWS = isWhiteSpace(nextChar);
if (stateSpecial && isSpecialChar(_char10)) {
return true;
}
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (!isSingleValueTag) {
return isWS === false; // return (isEQ || isWS) === false;
}
return true;
};
var _name2 = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(_Token.TYPE_ATTR_VALUE, unq(_name2));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
return TAG_STATE_ATTR;
}
if (escapeTags) {
if (isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
return TAG_STATE_NAME;
}
function stateTag() {
var currChar = chars.getCurr();
if (currChar === openTag) {
var nextChar = chars.getNext();
chars.skip(); // detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
var substr = chars.substrUntilChar(closeTag);
var hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
} // [myTag ]
var isNoAttrsInTag = substr.indexOf(_char14.EQ) === -1; // [/myTag]
var isClosingTag = substr[0] === _char14.SLASH;
if (isNoAttrsInTag || isClosingTag) {
var name = chars.grabWhile(function (_char11) {
return _char11 !== closeTag;
});
chars.skip(); // skip closeTag
emitToken(_Token.TYPE_TAG, name);
return STATE_WORD;
}
var _str = bufferGrabber.grabWhile(function (_char8) {
return isCharToken(_char8) && !isEscapeChar(_char8);
});
return STATE_TAG_ATTRS;
}
return emitToken(createToken(_Token.TYPE_WORD, _str, row, col));
if (currChar === closeTag) {
chars.skip();
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
var str = bufferGrabber.grabWhile(function (_char9) {
return isCharToken(_char9);
return STATE_WORD;
}
function stateAttrs() {
var silent = true;
var tagStr = chars.grabWhile(function (_char12) {
return _char12 !== closeTag;
}, silent);
var tagGrabber = (0, _utils.createCharGrabber)(tagStr, {
onSkip: onSkip
});
return emitToken(createToken(_Token.TYPE_WORD, str, row, col));
};
var hasSpace = tagGrabber.includes(_char14.SPACE);
var processTag = function processTag() {
var currChar = bufferGrabber.getCurr();
var nextChar = bufferGrabber.getNext();
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
chars.skip(); // skip closeTag
switchMode(STATE_WORD);
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(_Token.TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
return STATE_WORD;
}
if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
if (isWhiteSpace(chars.getCurr())) {
emitToken(_Token.TYPE_SPACE, chars.grabWhile(isWhiteSpace));
return STATE_WORD;
}
var str = bufferGrabber.grabWhile(function (val) {
return val !== closeTag;
});
var hasInvalidChars = str.length === 0 || str.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
return emitToken(createToken(_Token.TYPE_WORD, currChar, row, col));
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
bufferGrabber.skip(); // skip closeTag
// [myTag ]
emitToken(_Token.TYPE_WORD, chars.getCurr());
chars.skip();
return STATE_WORD;
}
var isNoAttrsInTag = str.indexOf(_char10.EQ) === -1; // [/myTag]
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
var currChar = chars.getCurr();
var nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
var isClosingTag = str[0] === _char10.SLASH;
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
if (isNoAttrsInTag || isClosingTag) {
return emitToken(createToken(_Token.TYPE_TAG, str, row, col));
emitToken(_Token.TYPE_WORD, nextChar);
return STATE_WORD;
}
emitToken(_Token.TYPE_WORD, currChar);
return STATE_WORD;
}
var isChar = function isChar(_char13) {
return isCharToken(_char13) && !isEscapeChar(_char13);
};
emitToken(_Token.TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
return switchMode(STATE_WORD);
};
emitToken(_Token.TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
var processAttrName = function processAttrName() {};
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
var processAttrValue = function processAttrValue() {};
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
var modeMap = (_modeMap = {}, _modeMap[STATE_WORD] = processWord, _modeMap[STATE_TAG] = processTag, _modeMap[STATE_ATTR_NAME] = processAttrName, _modeMap[STATE_ATTR_VALUE] = processAttrValue, _modeMap);
case STATE_WORD:
stateMode = stateWord();
break;
var tokenize = function tokenize() {
while (bufferGrabber.hasNext()) {
modeMap[mode](bufferGrabber);
default:
stateMode = STATE_WORD;
break;
}
}

@@ -227,9 +382,9 @@

return tokens;
};
}
var isTokenNested = function isTokenNested(token) {
var value = openTag + _char10.SLASH + token.getValue(); // potential bottleneck
function isTokenNested(token) {
var value = openTag + _char14.SLASH + token.getValue(); // potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -236,0 +391,0 @@ return {

12

lib/parse.js

@@ -8,3 +8,3 @@ "use strict";

var _pluginHelper = require("@bbob/plugin-helper");
var _index = require("@bbob/plugin-helper/lib/index");

@@ -38,3 +38,3 @@ var _lexer = require("./lexer");

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -46,3 +46,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -54,3 +54,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -62,3 +62,3 @@

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -141,3 +141,3 @@

if (Array.isArray(items)) {
if ((0, _pluginHelper.isTagNode)(node)) {
if ((0, _index.isTagNode)(node)) {
if (isAllowedTag(node.tag)) {

@@ -144,0 +144,0 @@ items.push(node.toTagNode());

23

lib/Token.js

@@ -17,8 +17,14 @@ "use strict";

var TOKEN_TYPE_WORD = 'word';
var TOKEN_TYPE_TAG = 'tag';
var TOKEN_TYPE_ATTR_NAME = 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 'attr-value';
var TOKEN_TYPE_SPACE = 'space';
var TOKEN_TYPE_NEW_LINE = 'new-line';
var TOKEN_TYPE_WORD = 1; // 'word';
var TOKEN_TYPE_TAG = 2; // 'tag';
var TOKEN_TYPE_ATTR_NAME = 3; // 'attr-name';
var TOKEN_TYPE_ATTR_VALUE = 4; // 'attr-value';
var TOKEN_TYPE_SPACE = 5; // 'space';
var TOKEN_TYPE_NEW_LINE = 6; // 'new-line';
/**

@@ -127,3 +133,3 @@ * @param {Token} token

function Token(type, value, line, row) {
this[TOKEN_TYPE_ID] = String(type);
this[TOKEN_TYPE_ID] = Number(type);
this[TOKEN_VALUE_ID] = String(value);

@@ -137,3 +143,4 @@ this[TOKEN_LINE_ID] = Number(line);

_proto.isEmpty = function isEmpty() {
return !!this[TOKEN_TYPE_ID];
// eslint-disable-next-line no-restricted-globals
return isNaN(this[TOKEN_TYPE_ID]);
};

@@ -140,0 +147,0 @@

256

lib/utils.js

@@ -8,105 +8,136 @@ "use strict";

/**
* @typedef {Object} CharGrabber
* @property {Function} skip
* @property {Function} hasNext
* @property {Function} isLast
* @property {Function} grabWhile
*/
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @returns
*/
var createCharGrabber = function createCharGrabber(source, options) {
// let idx = 0;
function CharGrabber(source, options) {
var cursor = {
pos: 0,
length: source.length
len: source.length
};
var skip = function skip() {
cursor.pos += 1;
var substrUntilChar = function substrUntilChar(_char) {
var pos = cursor.pos;
var idx = source.indexOf(_char, pos);
return idx >= 0 ? source.substr(pos, idx - pos) : '';
};
if (options && options.onSkip) {
options.onSkip();
}
var includes = function includes(val) {
return source.indexOf(val, cursor.pos) >= 0;
};
var hasNext = function hasNext() {
return cursor.length > cursor.pos;
return cursor.len > cursor.pos;
};
var getRest = function getRest() {
var isLast = function isLast() {
return cursor.pos === cursor.len;
};
var skip = function skip(num, silent) {
if (num === void 0) {
num = 1;
}
cursor.pos += num;
if (options && options.onSkip && !silent) {
options.onSkip();
}
};
var rest = function rest() {
return source.substr(cursor.pos);
};
var getCurr = function getCurr() {
var curr = function curr() {
return source[cursor.pos];
};
return {
skip: skip,
hasNext: hasNext,
isLast: function isLast() {
return cursor.pos === cursor.length;
},
var prev = function prev() {
var prevPos = cursor.pos - 1;
return typeof source[prevPos] !== 'undefined' ? source[prevPos] : null;
};
/**
* @param {Function} cond
* @returns {string}
*/
grabWhile: function grabWhile(cond) {
var start = 0;
var next = function next() {
var nextPos = cursor.pos + 1;
return nextPos <= source.length - 1 ? source[nextPos] : null;
};
if (hasNext()) {
start = cursor.pos;
var grabWhile = function grabWhile(cond, silent) {
var start = 0;
while (hasNext() && cond(getCurr())) {
skip();
}
if (hasNext()) {
start = cursor.pos;
while (hasNext() && cond(curr())) {
skip(1, silent);
}
}
return source.substr(start, cursor.pos - start);
},
getNext: function getNext() {
var nextPos = cursor.pos + 1;
return source.substr(start, cursor.pos - start);
};
/**
* @type {skip}
*/
if (nextPos <= source.length - 1) {
return source[nextPos];
}
return null;
},
getPrev: function getPrev() {
var prevPos = cursor.pos - 1;
this.skip = skip;
/**
* @returns {Boolean}
*/
if (typeof source[prevPos] !== 'undefined') {
return source[prevPos];
}
this.hasNext = hasNext;
/**
* @returns {String}
*/
return null;
},
getCurr: getCurr,
getRest: getRest,
this.getCurr = curr;
/**
* @returns {String}
*/
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
substrUntilChar: function substrUntilChar(_char) {
var restStr = getRest();
var indexOfChar = restStr.indexOf(_char);
this.getRest = rest;
/**
* @returns {String}
*/
if (indexOfChar >= 0) {
return restStr.substr(0, indexOfChar);
}
this.getNext = next;
/**
* @returns {String}
*/
return '';
}
};
this.getPrev = prev;
/**
* @returns {Boolean}
*/
this.isLast = isLast;
/**
* @returns {Boolean}
*/
this.includes = includes;
/**
* @param {Function} cond
* @param {Boolean} silent
* @return {String}
*/
this.grabWhile = grabWhile;
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
this.substrUntilChar = substrUntilChar;
}
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @return CharGrabber
*/
var createCharGrabber = function createCharGrabber(source, options) {
return new CharGrabber(source, options);
};

@@ -150,21 +181,6 @@ /**

};
/**
* @typedef {Object} ItemList
* @type {Object}
* @property {getLastCb} getLast
* @property {flushLastCb} flushLast
* @property {pushCb} push
* @property {toArrayCb} toArray
*/
/**
*
* @param values
* @return {ItemList}
*/
exports.unquote = unquote;
var createList = function createList(values) {
function NodeList(values) {
if (values === void 0) {

@@ -175,51 +191,39 @@ values = [];

var nodes = values;
/**
* @callback getLastCb
*/
var getLast = function getLast() {
if (Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined') {
return nodes[nodes.length - 1];
}
return null;
return Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined' ? nodes[nodes.length - 1] : null;
};
/**
* @callback flushLastCb
* @return {*}
*/
var flushLast = function flushLast() {
if (nodes.length) {
return nodes.pop();
}
return false;
return nodes.length ? nodes.pop() : false;
};
/**
* @callback pushCb
* @param value
*/
var push = function push(value) {
return nodes.push(value);
};
/**
* @callback toArrayCb
* @return {Array}
*/
var toArray = function toArray() {
return nodes;
};
return {
getLast: getLast,
flushLast: flushLast,
push: push,
toArray: function toArray() {
return nodes;
}
};
this.push = push;
this.toArray = toArray;
this.getLast = getLast;
this.flushLast = flushLast;
}
/**
*
* @param values
* @return {NodeList}
*/
var createList = function createList(values) {
if (values === void 0) {
values = [];
}
return new NodeList(values);
};
exports.createList = createList;

8

package.json
{
"name": "@bbob/parser",
"version": "2.5.8",
"version": "2.6.0",
"description": "Just parses BBcode to AST array. Part of @bbob bbcode parser",

@@ -16,3 +16,3 @@ "keywords": [

"dependencies": {
"@bbob/plugin-helper": "^2.5.8"
"@bbob/plugin-helper": "^2.6.0"
},

@@ -39,3 +39,3 @@ "main": "lib/index.js",

"build": "npm run build:commonjs && npm run build:es && npm run build:umd",
"test": "../../node_modules/.bin/jest --",
"test": "../../node_modules/.bin/jest",
"cover": "../../node_modules/.bin/jest --coverage",

@@ -67,3 +67,3 @@ "lint": "../../node_modules/.bin/eslint .",

],
"gitHead": "2eb1fbcccf065a95df2c1a28020119582d4a64d1"
"gitHead": "99f503df0cc35d33c9e57d49b6581631d49ab6c3"
}

329

src/lexer.js

@@ -24,3 +24,3 @@ /* eslint-disable no-plusplus,no-param-reassign */

* Creates a Token entity class
* @param {String} type
* @param {Number} type
* @param {String} value

@@ -48,2 +48,10 @@ * @param {Number} r line number

function createLexer(buffer, options = {}) {
const STATE_WORD = 0;
const STATE_TAG = 1;
const STATE_TAG_ATTRS = 2;
const TAG_STATE_NAME = 0;
const TAG_STATE_ATTR = 1;
const TAG_STATE_VALUE = 2;
let row = 0;

@@ -53,6 +61,10 @@ let col = 0;

let tokenIndex = -1;
let stateMode = STATE_WORD;
let tagMode = TAG_STATE_NAME;
const tokens = new Array(Math.floor(buffer.length));
const openTag = options.openTag || OPEN_BRAKET;
const closeTag = options.closeTag || CLOSE_BRAKET;
const escapeTags = options.enableEscapeTags;
const escapeTags = !!options.enableEscapeTags;
const onToken = options.onToken || (() => {
});

@@ -68,2 +80,3 @@ const RESERVED_CHARS = [closeTag, openTag, QUOTEMARK, BACKSLASH, SPACE, TAB, EQ, N, EM];

const isCharReserved = (char) => (RESERVED_CHARS.indexOf(char) >= 0);
const isNewLine = (char) => char === N;
const isWhiteSpace = (char) => (WHITESPACES.indexOf(char) >= 0);

@@ -74,154 +87,244 @@ const isCharToken = (char) => (NOT_CHAR_TOKENS.indexOf(char) === -1);

const isEscapeChar = (char) => char === BACKSLASH;
const onSkip = () => {
col++;
};
const unq = (val) => unquote(trimChar(val, QUOTEMARK));
const chars = createCharGrabber(buffer, { onSkip });
/**
* Emits newly created token to subscriber
* @param token
* @param {Number} type
* @param {String} value
*/
const emitToken = (token) => {
if (options.onToken) {
options.onToken(token);
}
function emitToken(type, value) {
const token = createToken(type, value, row, col);
onToken(token);
tokenIndex += 1;
tokens[tokenIndex] = token;
};
}
/**
* Parses params inside [myTag---params goes here---]content[/myTag]
* @param str
* @returns {{tag: *, attrs: Array}}
*/
const parseAttrs = (str) => {
let tagName = null;
let skipSpecialChars = false;
function nextTagState(tagChars, isSingleValueTag) {
if (tagMode === TAG_STATE_ATTR) {
const validAttrName = (char) => !(char === EQ || isWhiteSpace(char));
const name = tagChars.grabWhile(validAttrName);
const isEnd = tagChars.isLast();
const isValue = tagChars.getCurr() !== EQ;
const attrTokens = [];
const attrCharGrabber = createCharGrabber(str);
tagChars.skip();
const validAttr = (char) => {
const isEQ = char === EQ;
const isWS = isWhiteSpace(char);
const prevChar = attrCharGrabber.getPrev();
const nextChar = attrCharGrabber.getNext();
const isPrevSLASH = prevChar === BACKSLASH;
const isTagNameEmpty = tagName === null;
if (isEnd || isValue) {
emitToken(TYPE_ATTR_VALUE, unq(name));
} else {
emitToken(TYPE_ATTR_NAME, name);
}
if (isTagNameEmpty) {
return (isEQ || isWS || attrCharGrabber.isLast()) === false;
if (isEnd) {
return TAG_STATE_NAME;
}
if (skipSpecialChars && isSpecialChar(char)) {
return true;
if (isValue) {
return TAG_STATE_ATTR;
}
if (char === QUOTEMARK && !isPrevSLASH) {
skipSpecialChars = !skipSpecialChars;
return TAG_STATE_VALUE;
}
if (tagMode === TAG_STATE_VALUE) {
let stateSpecial = false;
if (!skipSpecialChars && !(nextChar === EQ || isWhiteSpace(nextChar))) {
return false;
const validAttrValue = (char) => {
// const isEQ = char === EQ;
const isQM = char === QUOTEMARK;
const prevChar = tagChars.getPrev();
const nextChar = tagChars.getNext();
const isPrevSLASH = prevChar === BACKSLASH;
const isNextEQ = nextChar === EQ;
const isWS = isWhiteSpace(char);
// const isPrevWS = isWhiteSpace(prevChar);
const isNextWS = isWhiteSpace(nextChar);
if (stateSpecial && isSpecialChar(char)) {
return true;
}
if (isQM && !isPrevSLASH) {
stateSpecial = !stateSpecial;
if (!stateSpecial && !(isNextEQ || isNextWS)) {
return false;
}
}
if (!isSingleValueTag) {
return isWS === false;
// return (isEQ || isWS) === false;
}
return true;
};
const name = tagChars.grabWhile(validAttrValue);
tagChars.skip();
emitToken(TYPE_ATTR_VALUE, unq(name));
if (tagChars.isLast()) {
return TAG_STATE_NAME;
}
return (isEQ || isWS) === false;
};
return TAG_STATE_ATTR;
}
const nextAttr = () => {
const attrStr = attrCharGrabber.grabWhile(validAttr);
const currChar = attrCharGrabber.getCurr();
const validName = (char) => !(char === EQ || isWhiteSpace(char) || tagChars.isLast());
const name = tagChars.grabWhile(validName);
// first string before space is a tag name [tagName params...]
if (tagName === null) {
tagName = attrStr;
} else if (isWhiteSpace(currChar) || currChar === QUOTEMARK || !attrCharGrabber.hasNext()) {
const escaped = unquote(trimChar(attrStr, QUOTEMARK));
attrTokens.push(createToken(TYPE_ATTR_VALUE, escaped, row, col));
} else {
attrTokens.push(createToken(TYPE_ATTR_NAME, attrStr, row, col));
emitToken(TYPE_TAG, name);
tagChars.skip();
// in cases when we has [url=someval]GET[/url] and we dont need to parse all
if (isSingleValueTag) {
return TAG_STATE_VALUE;
}
const hasEQ = tagChars.includes(EQ);
return hasEQ ? TAG_STATE_ATTR : TAG_STATE_VALUE;
}
function stateTag() {
const currChar = chars.getCurr();
if (currChar === openTag) {
const nextChar = chars.getNext();
chars.skip();
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
const substr = chars.substrUntilChar(closeTag);
const hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isCharReserved(nextChar) || hasInvalidChars || chars.isLast()) {
emitToken(TYPE_WORD, currChar);
return STATE_WORD;
}
attrCharGrabber.skip();
};
// [myTag ]
const isNoAttrsInTag = substr.indexOf(EQ) === -1;
// [/myTag]
const isClosingTag = substr[0] === SLASH;
while (attrCharGrabber.hasNext()) {
nextAttr();
if (isNoAttrsInTag || isClosingTag) {
const name = chars.grabWhile((char) => char !== closeTag);
chars.skip(); // skip closeTag
emitToken(TYPE_TAG, name);
return STATE_WORD;
}
return STATE_TAG_ATTRS;
}
return { tag: tagName, attrs: attrTokens };
};
return STATE_WORD;
}
const bufferGrabber = createCharGrabber(buffer, {
onSkip: () => {
col++;
},
});
function stateAttrs() {
const silent = true;
const tagStr = chars.grabWhile((char) => char !== closeTag, silent);
const tagGrabber = createCharGrabber(tagStr, { onSkip });
const hasSpace = tagGrabber.includes(SPACE);
const next = () => {
const currChar = bufferGrabber.getCurr();
const nextChar = bufferGrabber.getNext();
while (tagGrabber.hasNext()) {
tagMode = nextTagState(tagGrabber, !hasSpace);
}
if (currChar === N) {
bufferGrabber.skip();
chars.skip(); // skip closeTag
return STATE_WORD;
}
function stateWord() {
if (isNewLine(chars.getCurr())) {
emitToken(TYPE_NEW_LINE, chars.getCurr());
chars.skip();
col = 0;
row++;
emitToken(createToken(TYPE_NEW_LINE, currChar, row, col));
} else if (isWhiteSpace(currChar)) {
const str = bufferGrabber.grabWhile(isWhiteSpace);
emitToken(createToken(TYPE_SPACE, str, row, col));
} else if (escapeTags && isEscapeChar(currChar) && isEscapableChar(nextChar)) {
bufferGrabber.skip(); // skip the \ without emitting anything
bufferGrabber.skip(); // skip past the [, ] or \ as well
emitToken(createToken(TYPE_WORD, nextChar, row, col));
} else if (currChar === openTag) {
bufferGrabber.skip(); // skip openTag
return STATE_WORD;
}
// detect case where we have '[My word [tag][/tag]' or we have '[My last line word'
const substr = bufferGrabber.substrUntilChar(closeTag);
const hasInvalidChars = substr.length === 0 || substr.indexOf(openTag) >= 0;
if (isWhiteSpace(chars.getCurr())) {
emitToken(TYPE_SPACE, chars.grabWhile(isWhiteSpace));
if (isCharReserved(nextChar) || hasInvalidChars || bufferGrabber.isLast()) {
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else {
const str = bufferGrabber.grabWhile((val) => val !== closeTag);
return STATE_WORD;
}
bufferGrabber.skip(); // skip closeTag
// [myTag ]
const isNoAttrsInTag = str.indexOf(EQ) === -1;
// [/myTag]
const isClosingTag = str[0] === SLASH;
if (chars.getCurr() === openTag) {
if (chars.includes(closeTag)) {
return STATE_TAG;
}
if (isNoAttrsInTag || isClosingTag) {
emitToken(createToken(TYPE_TAG, str, row, col));
} else {
const parsed = parseAttrs(str);
emitToken(TYPE_WORD, chars.getCurr());
emitToken(createToken(TYPE_TAG, parsed.tag, row, col));
chars.skip();
parsed.attrs.map(emitToken);
return STATE_WORD;
}
if (escapeTags) {
if (isEscapeChar(chars.getCurr())) {
const currChar = chars.getCurr();
const nextChar = chars.getNext();
chars.skip(); // skip the \ without emitting anything
if (isEscapableChar(nextChar)) {
chars.skip(); // skip past the [, ] or \ as well
emitToken(TYPE_WORD, nextChar);
return STATE_WORD;
}
emitToken(TYPE_WORD, currChar);
return STATE_WORD;
}
} else if (currChar === closeTag) {
bufferGrabber.skip(); // skip closeTag
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else if (isCharToken(currChar)) {
if (escapeTags && isEscapeChar(currChar) && !isEscapableChar(nextChar)) {
bufferGrabber.skip();
emitToken(createToken(TYPE_WORD, currChar, row, col));
} else {
const str = bufferGrabber.grabWhile((char) => {
if (escapeTags) {
return isCharToken(char) && !isEscapeChar(char);
}
return isCharToken(char);
});
const isChar = (char) => isCharToken(char) && !isEscapeChar(char);
emitToken(createToken(TYPE_WORD, str, row, col));
}
emitToken(TYPE_WORD, chars.grabWhile(isChar));
return STATE_WORD;
}
};
const tokenize = () => {
while (bufferGrabber.hasNext()) {
next();
emitToken(TYPE_WORD, chars.grabWhile(isCharToken));
return STATE_WORD;
}
function tokenize() {
while (chars.hasNext()) {
switch (stateMode) {
case STATE_TAG:
stateMode = stateTag();
break;
case STATE_TAG_ATTRS:
stateMode = stateAttrs();
break;
case STATE_WORD:
stateMode = stateWord();
break;
default:
stateMode = STATE_WORD;
break;
}
}

@@ -232,9 +335,9 @@

return tokens;
};
}
const isTokenNested = (token) => {
function isTokenNested(token) {
const value = openTag + SLASH + token.getValue();
// potential bottleneck
return buffer.indexOf(value) > -1;
};
}

@@ -241,0 +344,0 @@ return {

10

src/parse.js
import TagNode from '@bbob/plugin-helper/lib/TagNode';
import { isTagNode } from '@bbob/plugin-helper';
import { isTagNode } from '@bbob/plugin-helper/lib/index';
import { createLexer } from './lexer';

@@ -25,3 +25,3 @@ import { createList } from './utils';

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -32,3 +32,3 @@ const nodes = createList();

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -39,3 +39,3 @@ const nestedNodes = createList();

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -46,3 +46,3 @@ const tagNodes = createList();

* @private
* @type {ItemList}
* @type {NodeList}
*/

@@ -49,0 +49,0 @@ const tagNodesAttrName = createList();

17

src/Token.js

@@ -13,8 +13,8 @@ import {

const TOKEN_TYPE_WORD = 'word';
const TOKEN_TYPE_TAG = 'tag';
const TOKEN_TYPE_ATTR_NAME = 'attr-name';
const TOKEN_TYPE_ATTR_VALUE = 'attr-value';
const TOKEN_TYPE_SPACE = 'space';
const TOKEN_TYPE_NEW_LINE = 'new-line';
const TOKEN_TYPE_WORD = 1; // 'word';
const TOKEN_TYPE_TAG = 2; // 'tag';
const TOKEN_TYPE_ATTR_NAME = 3; // 'attr-name';
const TOKEN_TYPE_ATTR_VALUE = 4; // 'attr-value';
const TOKEN_TYPE_SPACE = 5; // 'space';
const TOKEN_TYPE_NEW_LINE = 6; // 'new-line';

@@ -109,3 +109,3 @@ /**

constructor(type, value, line, row) {
this[TOKEN_TYPE_ID] = String(type);
this[TOKEN_TYPE_ID] = Number(type);
this[TOKEN_VALUE_ID] = String(value);

@@ -117,3 +117,4 @@ this[TOKEN_LINE_ID] = Number(line);

isEmpty() {
return !!this[TOKEN_TYPE_ID];
// eslint-disable-next-line no-restricted-globals
return isNaN(this[TOKEN_TYPE_ID]);
}

@@ -120,0 +121,0 @@

228

src/utils.js

@@ -6,93 +6,105 @@ import {

/**
* @typedef {Object} CharGrabber
* @property {Function} skip
* @property {Function} hasNext
* @property {Function} isLast
* @property {Function} grabWhile
*/
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @returns
*/
export const createCharGrabber = (source, options) => {
// let idx = 0;
function CharGrabber(source, options) {
const cursor = {
pos: 0,
length: source.length,
len: source.length,
};
const skip = () => {
cursor.pos += 1;
const substrUntilChar = (char) => {
const { pos } = cursor;
const idx = source.indexOf(char, pos);
if (options && options.onSkip) {
return idx >= 0 ? source.substr(pos, idx - pos) : '';
};
const includes = (val) => source.indexOf(val, cursor.pos) >= 0;
const hasNext = () => cursor.len > cursor.pos;
const isLast = () => cursor.pos === cursor.len;
const skip = (num = 1, silent) => {
cursor.pos += num;
if (options && options.onSkip && !silent) {
options.onSkip();
}
};
const hasNext = () => cursor.length > cursor.pos;
const getRest = () => source.substr(cursor.pos);
const getCurr = () => source[cursor.pos];
const rest = () => source.substr(cursor.pos);
const curr = () => source[cursor.pos];
const prev = () => {
const prevPos = cursor.pos - 1;
return {
skip,
hasNext,
isLast: () => (cursor.pos === cursor.length),
/**
* @param {Function} cond
* @returns {string}
*/
grabWhile: (cond) => {
let start = 0;
return typeof source[prevPos] !== 'undefined' ? source[prevPos] : null;
};
const next = () => {
const nextPos = cursor.pos + 1;
if (hasNext()) {
start = cursor.pos;
return nextPos <= (source.length - 1) ? source[nextPos] : null;
};
const grabWhile = (cond, silent) => {
let start = 0;
while (hasNext() && cond(getCurr())) {
skip();
}
}
if (hasNext()) {
start = cursor.pos;
return source.substr(start, cursor.pos - start);
},
getNext: () => {
const nextPos = cursor.pos + 1;
if (nextPos <= (source.length - 1)) {
return source[nextPos];
while (hasNext() && cond(curr())) {
skip(1, silent);
}
return null;
},
getPrev: () => {
const prevPos = cursor.pos - 1;
}
if (typeof source[prevPos] !== 'undefined') {
return source[prevPos];
}
return null;
},
getCurr,
getRest,
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
substrUntilChar: (char) => {
const restStr = getRest();
const indexOfChar = restStr.indexOf(char);
if (indexOfChar >= 0) {
return restStr.substr(0, indexOfChar);
}
return '';
},
return source.substr(start, cursor.pos - start);
};
};
/**
* @type {skip}
*/
this.skip = skip;
/**
* @returns {Boolean}
*/
this.hasNext = hasNext;
/**
* @returns {String}
*/
this.getCurr = curr;
/**
* @returns {String}
*/
this.getRest = rest;
/**
* @returns {String}
*/
this.getNext = next;
/**
* @returns {String}
*/
this.getPrev = prev;
/**
* @returns {Boolean}
*/
this.isLast = isLast;
/**
* @returns {Boolean}
*/
this.includes = includes;
/**
* @param {Function} cond
* @param {Boolean} silent
* @return {String}
*/
this.grabWhile = grabWhile;
/**
* Grabs rest of string until it find a char
* @param {String} char
* @return {String}
*/
this.substrUntilChar = substrUntilChar;
}
/**
* Creates a grabber wrapper for source string, that helps to iterate over string char by char
* @param {String} source
* @param {Object} options
* @param {Function} options.onSkip
* @return CharGrabber
*/
export const createCharGrabber = (source, options) => new CharGrabber(source, options);
/**
* Trims string from start and end by char

@@ -126,56 +138,24 @@ * @example

/**
* @typedef {Object} ItemList
* @type {Object}
* @property {getLastCb} getLast
* @property {flushLastCb} flushLast
* @property {pushCb} push
* @property {toArrayCb} toArray
*/
function NodeList(values = []) {
const nodes = values;
const getLast = () => (
Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined'
? nodes[nodes.length - 1]
: null);
const flushLast = () => (nodes.length ? nodes.pop() : false);
const push = (value) => nodes.push(value);
const toArray = () => nodes;
this.push = push;
this.toArray = toArray;
this.getLast = getLast;
this.flushLast = flushLast;
}
/**
*
* @param values
* @return {ItemList}
* @return {NodeList}
*/
export const createList = (values = []) => {
const nodes = values;
/**
* @callback getLastCb
*/
const getLast = () => {
if (Array.isArray(nodes) && nodes.length > 0 && typeof nodes[nodes.length - 1] !== 'undefined') {
return nodes[nodes.length - 1];
}
return null;
};
/**
* @callback flushLastCb
* @return {*}
*/
const flushLast = () => {
if (nodes.length) {
return nodes.pop();
}
return false;
};
/**
* @callback pushCb
* @param value
*/
const push = (value) => nodes.push(value);
/**
* @callback toArrayCb
* @return {Array}
*/
return {
getLast,
flushLast,
push,
toArray: () => nodes,
};
};
export const createList = (values = []) => new NodeList(values);
SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap
  • Changelog

About

Packages

npm

Go

Maven

PyPI

Rubygems

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc