Added logging, changed some directory structure

This commit is contained in:
2018-01-13 21:33:40 -05:00
parent f079a5f067
commit 8e72ffb917
73656 changed files with 35284 additions and 53718 deletions

View File

@@ -0,0 +1,2 @@
# Auto detect text files and perform LF normalization
* text eol=lf

View File

@@ -0,0 +1,2 @@
npm-debug.log
node_modules

View File

@@ -0,0 +1,5 @@
language: node_js
node_js:
- 0.8
- 0.10
- 0.11

View File

@@ -0,0 +1,18 @@
Copyright 2010, 2011, Chris Winberry <chris@winberry.net>. All rights reserved.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to
deal in the Software without restriction, including without limitation the
rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
IN THE SOFTWARE.

View File

@@ -0,0 +1,81 @@
#htmlparser2 [![NPM version](https://badge.fury.io/js/htmlparser2.png)](https://npmjs.org/package/htmlparser2) [![Build Status](https://secure.travis-ci.org/fb55/htmlparser2.png)](http://travis-ci.org/fb55/htmlparser2) [![Dependency Status](https://david-dm.org/fb55/htmlparser2.png)](https://david-dm.org/fb55/htmlparser2)
A forgiving HTML/XML/RSS parser written in JS for NodeJS. The parser can handle streams (chunked data) and supports custom handlers for writing custom DOMs/output.
##Installing
npm install htmlparser2
A live demo of htmlparser2 is available at http://demos.forbeslindesay.co.uk/htmlparser2/
##Usage
```javascript
var htmlparser = require("htmlparser2");
var parser = new htmlparser.Parser({
onopentag: function(name, attribs){
if(name === "script" && attribs.type === "text/javascript"){
console.log("JS! Hooray!");
}
},
ontext: function(text){
console.log("-->", text);
},
onclosetag: function(tagname){
if(tagname === "script"){
console.log("That's it?!");
}
}
});
parser.write("Xyz <script type='text/javascript'>var foo = '<<bar>>';</ script>");
parser.end();
```
Output (simplified):
```javascript
--> Xyz
JS! Hooray!
--> var foo = '<<bar>>';
That's it?!
```
Read more about the parser in the [wiki](https://github.com/fb55/htmlparser2/wiki/Parser-options).
##Get a DOM
The `DomHandler` (known as `DefaultHandler` in the original `htmlparser` module) produces a DOM (document object model) that can be manipulated using the [`DomUtils`](https://github.com/fb55/DomUtils) helper.
The `DomHandler`, while still bundled with this module, was moved to its [own module](https://github.com/fb55/domhandler). Have a look at it for further information.
##Parsing RSS/RDF/Atom Feeds
```javascript
new htmlparser.FeedHandler(function(<error> error, <object> feed){
...
});
```
##Performance
After having some artificial benchmarks for some time, __@AndreasMadsen__ published his [`htmlparser-benchmark`](https://github.com/AndreasMadsen/htmlparser-benchmark), which benchmarks HTML parses based on real-world websites.
At the time of writing, the latest versions of all supported parsers show the following performance characteristics on [Travis CI](https://travis-ci.org/AndreasMadsen/htmlparser-benchmark/builds/10805007) (please note that Travis doesn't guarantee equal conditions for all tests):
```
gumbo-parser : 34.9208 ms/file ± 21.4238
html-parser : 24.8224 ms/file ± 15.8703
html5 : 419.597 ms/file ± 264.265
htmlparser : 60.0722 ms/file ± 384.844
htmlparser2-dom: 12.0749 ms/file ± 6.49474
htmlparser2 : 7.49130 ms/file ± 5.74368
hubbub : 30.4980 ms/file ± 16.4682
libxmljs : 14.1338 ms/file ± 18.6541
parse5 : 22.0439 ms/file ± 15.3743
sax : 49.6513 ms/file ± 26.6032
```
##How is this different from [node-htmlparser](https://github.com/tautologistics/node-htmlparser)?
This is a fork of the `htmlparser` module. The main difference is that this is intended to be used only with node (it runs on other platforms using [browserify](https://github.com/substack/node-browserify)). `htmlparser2` was rewritten multiple times and, while it maintains an API that's compatible with `htmlparser` in most cases, the projects don't share any code anymore.
The parser now provides a callback interface close to [sax.js](https://github.com/isaacs/sax-js) (originally targeted at [readabilitySAX](https://github.com/fb55/readabilitysax)). As a result, old handlers won't work anymore.
The `DefaultHandler` and the `RssHandler` were renamed to clarify their purpose (to `DomHandler` and `FeedHandler`). The old names are still available when requiring `htmlparser2`, so your code should work as expected.

View File

@@ -0,0 +1,55 @@
module.exports = CollectingHandler;
function CollectingHandler(cbs){
this._cbs = cbs || {};
this.events = [];
}
var EVENTS = require("./").EVENTS;
Object.keys(EVENTS).forEach(function(name){
if(EVENTS[name] === 0){
name = "on" + name;
CollectingHandler.prototype[name] = function(){
this.events.push([name]);
if(this._cbs[name]) this._cbs[name]();
};
} else if(EVENTS[name] === 1){
name = "on" + name;
CollectingHandler.prototype[name] = function(a){
this.events.push([name, a]);
if(this._cbs[name]) this._cbs[name](a);
};
} else if(EVENTS[name] === 2){
name = "on" + name;
CollectingHandler.prototype[name] = function(a, b){
this.events.push([name, a, b]);
if(this._cbs[name]) this._cbs[name](a, b);
};
} else {
throw Error("wrong number of arguments");
}
});
CollectingHandler.prototype.onreset = function(){
this.events = [];
if(this._cbs.onreset) this._cbs.onreset();
};
CollectingHandler.prototype.restart = function(){
if(this._cbs.onreset) this._cbs.onreset();
for(var i = 0, len = this.events.length; i < len; i++){
if(this._cbs[this.events[i][0]]){
var num = this.events[i].length;
if(num === 1){
this._cbs[this.events[i][0]]();
} else if(num === 2){
this._cbs[this.events[i][0]](this.events[i][1]);
} else {
this._cbs[this.events[i][0]](this.events[i][1], this.events[i][2]);
}
}
}
};

View File

@@ -0,0 +1,95 @@
var index = require("./index.js"),
DomHandler = index.DomHandler,
DomUtils = index.DomUtils;
//TODO: make this a streamable handler
function FeedHandler(callback, options){
this.init(callback, options);
}
require("util").inherits(FeedHandler, DomHandler);
FeedHandler.prototype.init = DomHandler;
function getElements(what, where){
return DomUtils.getElementsByTagName(what, where, true);
}
function getOneElement(what, where){
return DomUtils.getElementsByTagName(what, where, true, 1)[0];
}
function fetch(what, where, recurse){
return DomUtils.getText(
DomUtils.getElementsByTagName(what, where, recurse, 1)
).trim();
}
function addConditionally(obj, prop, what, where, recurse){
var tmp = fetch(what, where, recurse);
if(tmp) obj[prop] = tmp;
}
var isValidFeed = function(value) {
return value === "rss" || value === "feed" || value === "rdf:RDF";
};
FeedHandler.prototype.onend = function() {
var feed = {},
feedRoot = getOneElement(isValidFeed, this.dom),
tmp, childs;
if (feedRoot) {
if(feedRoot.name === "feed"){
childs = feedRoot.children;
feed.type = "atom";
addConditionally(feed, "id", "id", childs);
addConditionally(feed, "title", "title", childs);
if((tmp = getOneElement("link", childs)) && (tmp = tmp.attribs) && (tmp = tmp.href)) feed.link = tmp;
addConditionally(feed, "description", "subtitle", childs);
if(tmp = fetch("updated", childs)) feed.updated = new Date(tmp);
addConditionally(feed, "author", "email", childs, true);
feed.items = getElements("entry", childs).map(function(item){
var entry = {}, tmp;
item = item.children;
addConditionally(entry, "id", "id", item);
addConditionally(entry, "title", "title", item);
if((tmp = getOneElement("link", item)) && (tmp = tmp.attribs) && (tmp = tmp.href)) entry.link = tmp;
addConditionally(entry, "description", "summary", item);
if(tmp = fetch("updated", item)) entry.pubDate = new Date(tmp);
return entry;
});
} else{
childs = getOneElement("channel", feedRoot.children).children;
feed.type = feedRoot.name.substr(0, 3);
feed.id = "";
addConditionally(feed, "title", "title", childs);
addConditionally(feed, "link", "link", childs);
addConditionally(feed, "description", "description", childs);
if(tmp = fetch("lastBuildDate", childs)) feed.updated = new Date(tmp);
addConditionally(feed, "author", "managingEditor", childs, true);
feed.items = getElements("item", feedRoot.children).map(function(item){
var entry = {}, tmp;
item = item.children;
addConditionally(entry, "id", "guid", item);
addConditionally(entry, "title", "title", item);
addConditionally(entry, "link", "link", item);
addConditionally(entry, "description", "description", item);
if(tmp = fetch("pubDate", item)) entry.pubDate = new Date(tmp);
return entry;
});
}
}
this.dom = feed;
DomHandler.prototype._handleCallback.call(
this, feedRoot ? null : Error("couldn't find root of feed")
);
};
module.exports = FeedHandler;

View File

@@ -0,0 +1,314 @@
var Tokenizer = require("./Tokenizer.js");
/*
Options:
xmlMode: Special behavior for script/style tags (true by default)
lowerCaseAttributeNames: call .toLowerCase for each attribute name (true if xmlMode is `false`)
lowerCaseTags: call .toLowerCase for each tag name (true if xmlMode is `false`)
*/
/*
Callbacks:
oncdataend,
oncdatastart,
onclosetag,
oncomment,
oncommentend,
onerror,
onopentag,
onprocessinginstruction,
onreset,
ontext
*/
var formTags = {
input: true,
option: true,
optgroup: true,
select: true,
button: true,
datalist: true,
textarea: true
};
var openImpliesClose = {
tr : { tr:true, th:true, td:true },
th : { th:true },
td : { thead:true, td:true },
body : { head:true, link:true, script:true },
li : { li:true },
p : { p:true },
select : formTags,
input : formTags,
output : formTags,
button : formTags,
datalist: formTags,
textarea: formTags,
option : { option:true },
optgroup: { optgroup:true }
};
var voidElements = {
__proto__: null,
area: true,
base: true,
basefont: true,
br: true,
col: true,
command: true,
embed: true,
frame: true,
hr: true,
img: true,
input: true,
isindex: true,
keygen: true,
link: true,
meta: true,
param: true,
source: true,
track: true,
wbr: true
};
var re_nameEnd = /\s|\//;
function Parser(cbs, options){
this._options = options || {};
this._cbs = cbs || {};
this._tagname = "";
this._attribname = "";
this._attribvalue = "";
this._attribs = null;
this._stack = [];
this._done = false;
this.startIndex = 0;
this.endIndex = null;
this._tokenizer = new Tokenizer(options, this);
}
require("util").inherits(Parser, require("events").EventEmitter);
Parser.prototype._updatePosition = function(initialOffset){
if(this.endIndex === null){
this.startIndex = this._tokenizer._sectionStart <= initialOffset ? 0 : this._tokenizer._sectionStart - initialOffset;
}
this.startIndex = this.endIndex + 1;
this.endIndex = this._tokenizer._index;
};
//Tokenizer event handlers
Parser.prototype.ontext = function(data){
this._updatePosition(1);
this.endIndex--;
if(this._cbs.ontext) this._cbs.ontext(data);
};
Parser.prototype.onopentagname = function(name){
if(!(this._options.xmlMode || "lowerCaseTags" in this._options) || this._options.lowerCaseTags){
name = name.toLowerCase();
}
this._tagname = name;
if (!this._options.xmlMode && name in openImpliesClose) {
for(
var el;
(el = this._stack[this._stack.length-1]) in openImpliesClose[name];
this.onclosetag(el)
);
}
if(this._options.xmlMode || !(name in voidElements)){
this._stack.push(name);
}
if(this._cbs.onopentagname) this._cbs.onopentagname(name);
if(this._cbs.onopentag) this._attribs = {};
};
Parser.prototype.onopentagend = function(){
this._updatePosition(1);
if(this._attribs){
if(this._cbs.onopentag) this._cbs.onopentag(this._tagname, this._attribs);
this._attribs = null;
}
if(!this._options.xmlMode && this._cbs.onclosetag && this._tagname in voidElements){
this._cbs.onclosetag(this._tagname);
}
this._tagname = "";
};
Parser.prototype.onclosetag = function(name){
this._updatePosition(1);
if(!(this._options.xmlMode || "lowerCaseTags" in this._options) || this._options.lowerCaseTags){
name = name.toLowerCase();
}
if(this._stack.length && (!(name in voidElements) || this._options.xmlMode)){
var pos = this._stack.lastIndexOf(name);
if(pos !== -1){
if(this._cbs.onclosetag){
pos = this._stack.length - pos;
while(pos--) this._cbs.onclosetag(this._stack.pop());
}
else this._stack.length = pos;
} else if(name === "p" && !this._options.xmlMode){
this.onopentagname(name);
this._closeCurrentTag();
}
} else if(!this._options.xmlMode && (name === "br" || name === "p")){
this.onopentagname(name);
this._closeCurrentTag();
}
};
Parser.prototype.onselfclosingtag = function(){
if(this._options.xmlMode){
this._closeCurrentTag();
} else {
this.onopentagend();
}
};
Parser.prototype._closeCurrentTag = function(){
var name = this._tagname;
this.onopentagend();
//self-closing tags will be on the top of the stack
//(cheaper check than in onclosetag)
if(this._stack[this._stack.length-1] === name){
if(this._cbs.onclosetag){
this._cbs.onclosetag(name);
}
this._stack.pop();
}
};
Parser.prototype.onattribname = function(name){
if(!(this._options.xmlMode || "lowerCaseAttributeNames" in this._options) || this._options.lowerCaseAttributeNames){
name = name.toLowerCase();
}
this._attribname = name;
};
Parser.prototype.onattribdata = function(value){
this._attribvalue += value;
};
Parser.prototype.onattribend = function(){
if(this._cbs.onattribute) this._cbs.onattribute(this._attribname, this._attribvalue);
if(
this._attribs &&
!Object.prototype.hasOwnProperty.call(this._attribs, this._attribname)
){
this._attribs[this._attribname] = this._attribvalue;
}
this._attribname = "";
this._attribvalue = "";
};
Parser.prototype.ondeclaration = function(value){
if(this._cbs.onprocessinginstruction){
var idx = value.search(re_nameEnd),
name = idx < 0 ? value : value.substr(0, idx);
if(!(this._options.xmlMode || "lowerCaseTags" in this._options) || this._options.lowerCaseTags){
name = name.toLowerCase();
}
this._cbs.onprocessinginstruction("!" + name, "!" + value);
}
};
Parser.prototype.onprocessinginstruction = function(value){
if(this._cbs.onprocessinginstruction){
var idx = value.search(re_nameEnd),
name = idx < 0 ? value : value.substr(0, idx);
if(!(this._options.xmlMode || "lowerCaseTags" in this._options) || this._options.lowerCaseTags){
name = name.toLowerCase();
}
this._cbs.onprocessinginstruction("?" + name, "?" + value);
}
};
Parser.prototype.oncomment = function(value){
this._updatePosition(4);
if(this._cbs.oncomment) this._cbs.oncomment(value);
if(this._cbs.oncommentend) this._cbs.oncommentend();
};
Parser.prototype.oncdata = function(value){
this._updatePosition(1);
if(this._options.xmlMode){
if(this._cbs.oncdatastart) this._cbs.oncdatastart();
if(this._cbs.ontext) this._cbs.ontext(value);
if(this._cbs.oncdataend) this._cbs.oncdataend();
} else {
this.oncomment("[CDATA[" + value + "]]");
}
};
Parser.prototype.onerror = function(err){
if(this._cbs.onerror) this._cbs.onerror(err);
};
Parser.prototype.onend = function(){
if(this._cbs.onclosetag){
for(
var i = this._stack.length;
i > 0;
this._cbs.onclosetag(this._stack[--i])
);
}
if(this._cbs.onend) this._cbs.onend();
};
//Resets the parser to a blank state, ready to parse a new HTML document
Parser.prototype.reset = function(){
if(this._cbs.onreset) this._cbs.onreset();
this._tokenizer.reset();
this._tagname = "";
this._attribname = "";
this._attribs = null;
this._stack = [];
this._done = false;
};
//Parses a complete HTML document and pushes it to the handler
Parser.prototype.parseComplete = function(data){
this.reset();
this.end(data);
};
Parser.prototype.write = function(chunk){
if(this._done) this.onerror(Error(".write() after done!"));
this._tokenizer.write(chunk);
};
Parser.prototype.end = function(chunk){
if(this._done) this.onerror(Error(".end() after done!"));
this._tokenizer.end(chunk);
this._done = true;
};
//alias for backwards compat
Parser.prototype.parseChunk = Parser.prototype.write;
Parser.prototype.done = Parser.prototype.end;
module.exports = Parser;

View File

@@ -0,0 +1,27 @@
module.exports = ProxyHandler;
var ProxyHandler = function(cbs){
this._cbs = cbs || {};
};
var EVENTS = require("./").EVENTS;
Object.keys(EVENTS).forEach(function(name){
if(EVENTS[name] === 0){
name = "on" + name;
ProxyHandler.prototype[name] = function(){
if(this._cbs[name]) this._cbs[name]();
};
} else if(EVENTS[name] === 1){
name = "on" + name;
ProxyHandler.prototype[name] = function(a){
if(this._cbs[name]) this._cbs[name](a);
};
} else if(EVENTS[name] === 2){
name = "on" + name;
ProxyHandler.prototype[name] = function(a, b){
if(this._cbs[name]) this._cbs[name](a, b);
};
} else {
throw Error("wrong number of arguments");
}
});

View File

@@ -0,0 +1,35 @@
module.exports = Stream;
var Parser = require("./WritableStream.js");
function Stream(options){
Parser.call(this, new Cbs(this), options);
}
require("util").inherits(Stream, Parser);
Stream.prototype.readable = true;
function Cbs(scope){
this.scope = scope;
}
var EVENTS = require("../").EVENTS;
Object.keys(EVENTS).forEach(function(name){
if(EVENTS[name] === 0){
Cbs.prototype["on" + name] = function(){
this.scope.emit(name);
};
} else if(EVENTS[name] === 1){
Cbs.prototype["on" + name] = function(a){
this.scope.emit(name, a);
};
} else if(EVENTS[name] === 2){
Cbs.prototype["on" + name] = function(a, b){
this.scope.emit(name, a, b);
};
} else {
throw Error("wrong number of arguments!");
}
});

View File

@@ -0,0 +1,876 @@
module.exports = Tokenizer;
var entityMap = require("./entities/entities.json"),
legacyMap = require("./entities/legacy.json"),
xmlMap = require("./entities/xml.json"),
decodeMap = require("./entities/decode.json"),
i = 0,
TEXT = i++,
BEFORE_TAG_NAME = i++, //after <
IN_TAG_NAME = i++,
IN_SELF_CLOSING_TAG = i++,
BEFORE_CLOSING_TAG_NAME = i++,
IN_CLOSING_TAG_NAME = i++,
AFTER_CLOSING_TAG_NAME = i++,
//attributes
BEFORE_ATTRIBUTE_NAME = i++,
IN_ATTRIBUTE_NAME = i++,
AFTER_ATTRIBUTE_NAME = i++,
BEFORE_ATTRIBUTE_VALUE = i++,
IN_ATTRIBUTE_VALUE_DQ = i++, // "
IN_ATTRIBUTE_VALUE_SQ = i++, // '
IN_ATTRIBUTE_VALUE_NQ = i++,
//declarations
BEFORE_DECLARATION = i++, // !
IN_DECLARATION = i++,
//processing instructions
IN_PROCESSING_INSTRUCTION = i++, // ?
//comments
BEFORE_COMMENT = i++,
IN_COMMENT = i++,
AFTER_COMMENT_1 = i++,
AFTER_COMMENT_2 = i++,
//cdata
BEFORE_CDATA_1 = i++, // [
BEFORE_CDATA_2 = i++, // C
BEFORE_CDATA_3 = i++, // D
BEFORE_CDATA_4 = i++, // A
BEFORE_CDATA_5 = i++, // T
BEFORE_CDATA_6 = i++, // A
IN_CDATA = i++,// [
AFTER_CDATA_1 = i++, // ]
AFTER_CDATA_2 = i++, // ]
//special tags
BEFORE_SPECIAL = i++, //S
BEFORE_SPECIAL_END = i++, //S
BEFORE_SCRIPT_1 = i++, //C
BEFORE_SCRIPT_2 = i++, //R
BEFORE_SCRIPT_3 = i++, //I
BEFORE_SCRIPT_4 = i++, //P
BEFORE_SCRIPT_5 = i++, //T
AFTER_SCRIPT_1 = i++, //C
AFTER_SCRIPT_2 = i++, //R
AFTER_SCRIPT_3 = i++, //I
AFTER_SCRIPT_4 = i++, //P
AFTER_SCRIPT_5 = i++, //T
BEFORE_STYLE_1 = i++, //T
BEFORE_STYLE_2 = i++, //Y
BEFORE_STYLE_3 = i++, //L
BEFORE_STYLE_4 = i++, //E
AFTER_STYLE_1 = i++, //T
AFTER_STYLE_2 = i++, //Y
AFTER_STYLE_3 = i++, //L
AFTER_STYLE_4 = i++, //E
BEFORE_ENTITY = i++, //&
BEFORE_NUMERIC_ENTITY = i++, //#
IN_NAMED_ENTITY = i++,
IN_NUMERIC_ENTITY = i++,
IN_HEX_ENTITY = i++, //X
j = 0,
SPECIAL_NONE = j++,
SPECIAL_SCRIPT = j++,
SPECIAL_STYLE = j++;
function whitespace(c){
return c === " " || c === "\n" || c === "\t" || c === "\f" || c === "\r";
}
function ifElseState(upper, SUCCESS, FAILURE){
var lower = upper.toLowerCase();
if(upper === lower){
return function(c){
this._state = c === lower ? SUCCESS : FAILURE;
};
} else {
return function(c){
this._state = (c === lower || c === upper) ? SUCCESS : FAILURE;
};
}
}
function consumeSpecialNameChar(upper, NEXT_STATE){
var lower = upper.toLowerCase();
return function(c){
if(c === lower || c === upper){
this._state = NEXT_STATE;
} else {
this._state = IN_TAG_NAME;
this._index--; //consume the token again
}
};
}
function Tokenizer(options, cbs){
this._state = TEXT;
this._buffer = "";
this._sectionStart = 0;
this._index = 0;
this._baseState = TEXT;
this._special = SPECIAL_NONE;
this._cbs = cbs;
this._running = true;
this._xmlMode = !!(options && options.xmlMode);
this._decodeEntities = !!(options && options.decodeEntities);
}
Tokenizer.prototype._stateText = function(c){
if(c === "<"){
if(this._index > this._sectionStart){
this._cbs.ontext(this._getSection());
}
this._state = BEFORE_TAG_NAME;
this._sectionStart = this._index;
} else if(this._decodeEntities && this._special === SPECIAL_NONE && c === "&"){
if(this._index > this._sectionStart){
this._cbs.ontext(this._getSection());
}
this._baseState = TEXT;
this._state = BEFORE_ENTITY;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateBeforeTagName = function(c){
if(c === "/"){
this._state = BEFORE_CLOSING_TAG_NAME;
} else if(c === ">" || this._special !== SPECIAL_NONE || whitespace(c)) {
this._state = TEXT;
} else if(c === "!"){
this._state = BEFORE_DECLARATION;
this._sectionStart = this._index + 1;
} else if(c === "?"){
this._state = IN_PROCESSING_INSTRUCTION;
this._sectionStart = this._index + 1;
} else if(c === "<"){
this._cbs.ontext(this._getSection());
this._sectionStart = this._index;
} else {
this._state = (!this._xmlMode && (c === "s" || c === "S")) ?
BEFORE_SPECIAL : IN_TAG_NAME;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInTagName = function(c){
if(c === "/" || c === ">" || whitespace(c)){
this._emitToken("onopentagname");
this._state = BEFORE_ATTRIBUTE_NAME;
this._index--;
}
};
Tokenizer.prototype._stateBeforeCloseingTagName = function(c){
if(whitespace(c));
else if(c === ">"){
this._state = TEXT;
} else if(this._special !== SPECIAL_NONE){
if(c === "s" || c === "S"){
this._state = BEFORE_SPECIAL_END;
} else {
this._state = TEXT;
this._index--;
}
} else {
this._state = IN_CLOSING_TAG_NAME;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInCloseingTagName = function(c){
if(c === ">" || whitespace(c)){
this._emitToken("onclosetag");
this._state = AFTER_CLOSING_TAG_NAME;
this._index--;
}
};
Tokenizer.prototype._stateAfterCloseingTagName = function(c){
//skip everything until ">"
if(c === ">"){
this._state = TEXT;
this._sectionStart = this._index + 1;
}
};
Tokenizer.prototype._stateBeforeAttributeName = function(c){
if(c === ">"){
this._cbs.onopentagend();
this._state = TEXT;
this._sectionStart = this._index + 1;
} else if(c === "/"){
this._state = IN_SELF_CLOSING_TAG;
} else if(!whitespace(c)){
this._state = IN_ATTRIBUTE_NAME;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInSelfClosingTag = function(c){
if(c === ">"){
this._cbs.onselfclosingtag();
this._state = TEXT;
this._sectionStart = this._index + 1;
} else if(!whitespace(c)){
this._state = BEFORE_ATTRIBUTE_NAME;
this._index--;
}
};
Tokenizer.prototype._stateInAttributeName = function(c){
if(c === "=" || c === "/" || c === ">" || whitespace(c)){
if(this._index > this._sectionStart){
this._cbs.onattribname(this._getSection());
}
this._sectionStart = -1;
this._state = AFTER_ATTRIBUTE_NAME;
this._index--;
}
};
Tokenizer.prototype._stateAfterAttributeName = function(c){
if(c === "="){
this._state = BEFORE_ATTRIBUTE_VALUE;
} else if(c === "/" || c === ">"){
this._cbs.onattribend();
this._state = BEFORE_ATTRIBUTE_NAME;
this._index--;
} else if(!whitespace(c)){
this._cbs.onattribend();
this._state = IN_ATTRIBUTE_NAME;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateBeforeAttributeValue = function(c){
if(c === "\""){
this._state = IN_ATTRIBUTE_VALUE_DQ;
this._sectionStart = this._index + 1;
} else if(c === "'"){
this._state = IN_ATTRIBUTE_VALUE_SQ;
this._sectionStart = this._index + 1;
} else if(!whitespace(c)){
this._state = IN_ATTRIBUTE_VALUE_NQ;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInAttributeValueDoubleQuotes = function(c){
if(c === "\""){
this._emitToken("onattribdata");
this._cbs.onattribend();
this._state = BEFORE_ATTRIBUTE_NAME;
} else if(this._decodeEntities && c === "&"){
this._emitToken("onattribdata");
this._baseState = this._state;
this._state = BEFORE_ENTITY;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInAttributeValueSingleQuotes = function(c){
if(c === "'"){
this._emitToken("onattribdata");
this._cbs.onattribend();
this._state = BEFORE_ATTRIBUTE_NAME;
} else if(this._decodeEntities && c === "&"){
this._emitToken("onattribdata");
this._baseState = this._state;
this._state = BEFORE_ENTITY;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateInAttributeValueNoQuotes = function(c){
if(whitespace(c) || c === ">"){
this._emitToken("onattribdata");
this._cbs.onattribend();
this._state = BEFORE_ATTRIBUTE_NAME;
this._index--;
} else if(this._decodeEntities && c === "&"){
this._emitToken("onattribdata");
this._baseState = this._state;
this._state = BEFORE_ENTITY;
this._sectionStart = this._index;
}
};
Tokenizer.prototype._stateBeforeDeclaration = function(c){
this._state = c === "[" ? BEFORE_CDATA_1 :
c === "-" ? BEFORE_COMMENT :
IN_DECLARATION;
};
Tokenizer.prototype._stateInDeclaration = function(c){
if(c === ">"){
this._cbs.ondeclaration(this._getSection());
this._state = TEXT;
this._sectionStart = this._index + 1;
}
};
Tokenizer.prototype._stateInProcessingInstruction = function(c){
if(c === ">"){
this._cbs.onprocessinginstruction(this._getSection());
this._state = TEXT;
this._sectionStart = this._index + 1;
}
};
Tokenizer.prototype._stateBeforeComment = function(c){
if(c === "-"){
this._state = IN_COMMENT;
this._sectionStart = this._index + 1;
} else {
this._state = IN_DECLARATION;
}
};
Tokenizer.prototype._stateInComment = function(c){
if(c === "-") this._state = AFTER_COMMENT_1;
};
Tokenizer.prototype._stateAfterComment1 = ifElseState("-", AFTER_COMMENT_2, IN_COMMENT);
Tokenizer.prototype._stateAfterComment2 = function(c){
if(c === ">"){
//remove 2 trailing chars
this._cbs.oncomment(this._buffer.substring(this._sectionStart, this._index - 2));
this._state = TEXT;
this._sectionStart = this._index + 1;
} else if(c !== "-"){
this._state = IN_COMMENT;
}
// else: stay in AFTER_COMMENT_2 (`--->`)
};
Tokenizer.prototype._stateBeforeCdata1 = ifElseState("C", BEFORE_CDATA_2, IN_DECLARATION);
Tokenizer.prototype._stateBeforeCdata2 = ifElseState("D", BEFORE_CDATA_3, IN_DECLARATION);
Tokenizer.prototype._stateBeforeCdata3 = ifElseState("A", BEFORE_CDATA_4, IN_DECLARATION);
Tokenizer.prototype._stateBeforeCdata4 = ifElseState("T", BEFORE_CDATA_5, IN_DECLARATION);
Tokenizer.prototype._stateBeforeCdata5 = ifElseState("A", BEFORE_CDATA_6, IN_DECLARATION);
Tokenizer.prototype._stateBeforeCdata6 = function(c){
if(c === "["){
this._state = IN_CDATA;
this._sectionStart = this._index + 1;
} else {
this._state = IN_DECLARATION;
}
};
Tokenizer.prototype._stateInCdata = function(c){
if(c === "]") this._state = AFTER_CDATA_1;
};
Tokenizer.prototype._stateAfterCdata1 = ifElseState("]", AFTER_CDATA_2, IN_CDATA);
Tokenizer.prototype._stateAfterCdata2 = function(c){
if(c === ">"){
//remove 2 trailing chars
this._cbs.oncdata(this._buffer.substring(this._sectionStart, this._index - 2));
this._state = TEXT;
this._sectionStart = this._index + 1;
} else if (c !== "]") {
this._state = IN_CDATA;
}
//else: stay in AFTER_CDATA_2 (`]]]>`)
};
Tokenizer.prototype._stateBeforeSpecial = function(c){
if(c === "c" || c === "C"){
this._state = BEFORE_SCRIPT_1;
} else if(c === "t" || c === "T"){
this._state = BEFORE_STYLE_1;
} else {
this._state = IN_TAG_NAME;
this._index--; //consume the token again
}
};
Tokenizer.prototype._stateBeforeSpecialEnd = function(c){
if(this._special === SPECIAL_SCRIPT && (c === "c" || c === "C")){
this._state = AFTER_SCRIPT_1;
} else if(this._special === SPECIAL_STYLE && (c === "t" || c === "T")){
this._state = AFTER_STYLE_1;
}
else this._state = TEXT;
};
Tokenizer.prototype._stateBeforeScript1 = consumeSpecialNameChar("R", BEFORE_SCRIPT_2);
Tokenizer.prototype._stateBeforeScript2 = consumeSpecialNameChar("I", BEFORE_SCRIPT_3);
Tokenizer.prototype._stateBeforeScript3 = consumeSpecialNameChar("P", BEFORE_SCRIPT_4);
Tokenizer.prototype._stateBeforeScript4 = consumeSpecialNameChar("T", BEFORE_SCRIPT_5);
Tokenizer.prototype._stateBeforeScript5 = function(c){
if(c === "/" || c === ">" || whitespace(c)){
this._special = SPECIAL_SCRIPT;
}
this._state = IN_TAG_NAME;
this._index--; //consume the token again
};
Tokenizer.prototype._stateAfterScript1 = ifElseState("R", AFTER_SCRIPT_2, TEXT);
Tokenizer.prototype._stateAfterScript2 = ifElseState("I", AFTER_SCRIPT_3, TEXT);
Tokenizer.prototype._stateAfterScript3 = ifElseState("P", AFTER_SCRIPT_4, TEXT);
Tokenizer.prototype._stateAfterScript4 = ifElseState("T", AFTER_SCRIPT_5, TEXT);
Tokenizer.prototype._stateAfterScript5 = function(c){
if(c === ">" || whitespace(c)){
this._special = SPECIAL_NONE;
this._state = IN_CLOSING_TAG_NAME;
this._sectionStart = this._index - 6;
this._index--; //reconsume the token
}
else this._state = TEXT;
};
Tokenizer.prototype._stateBeforeStyle1 = consumeSpecialNameChar("Y", BEFORE_STYLE_2);
Tokenizer.prototype._stateBeforeStyle2 = consumeSpecialNameChar("L", BEFORE_STYLE_3);
Tokenizer.prototype._stateBeforeStyle3 = consumeSpecialNameChar("E", BEFORE_STYLE_4);
Tokenizer.prototype._stateBeforeStyle4 = function(c){
if(c === "/" || c === ">" || whitespace(c)){
this._special = SPECIAL_STYLE;
}
this._state = IN_TAG_NAME;
this._index--; //consume the token again
};
Tokenizer.prototype._stateAfterStyle1 = ifElseState("Y", AFTER_STYLE_2, TEXT);
Tokenizer.prototype._stateAfterStyle2 = ifElseState("L", AFTER_STYLE_3, TEXT);
Tokenizer.prototype._stateAfterStyle3 = ifElseState("E", AFTER_STYLE_4, TEXT);
Tokenizer.prototype._stateAfterStyle4 = function(c){
if(c === ">" || whitespace(c)){
this._special = SPECIAL_NONE;
this._state = IN_CLOSING_TAG_NAME;
this._sectionStart = this._index - 5;
this._index--; //reconsume the token
}
else this._state = TEXT;
};
Tokenizer.prototype._stateBeforeEntity = ifElseState("#", BEFORE_NUMERIC_ENTITY, IN_NAMED_ENTITY);
Tokenizer.prototype._stateBeforeNumericEntity = ifElseState("X", IN_HEX_ENTITY, IN_NUMERIC_ENTITY);
//for entities within attributes
Tokenizer.prototype._parseNamedEntityStrict = function(){
//offset = 1
if(this._sectionStart + 1 < this._index){
var entity = this._buffer.substring(this._sectionStart + 1, this._index),
map = this._xmlMode ? xmlMap : entityMap;
if(map.hasOwnProperty(entity)){
this._emitPartial(map[entity]);
this._sectionStart = this._index + 1;
}
}
};
//parses legacy entities (without trailing semicolon)
Tokenizer.prototype._parseLegacyEntity = function(){
var start = this._sectionStart + 1,
limit = this._index - start;
if(limit > 6) limit = 6; //the max length of legacy entities is 6
while(limit >= 2){ //the min length of legacy entities is 2
var entity = this._buffer.substr(start, limit);
if(legacyMap.hasOwnProperty(entity)){
this._emitPartial(legacyMap[entity]);
this._sectionStart += limit + 2;
break;
} else {
limit--;
}
}
};
Tokenizer.prototype._stateInNamedEntity = function(c){
if(c === ";"){
this._parseNamedEntityStrict();
if(this._sectionStart + 1 < this._index && !this._xmlMode){
this._parseLegacyEntity();
}
this._state = this._baseState;
} else if((c < "a" || c > "z") && (c < "A" || c > "Z") && (c < "0" || c > "9")){
if(this._xmlMode);
else if(this._baseState !== TEXT){
if(c !== "="){
this._parseNamedEntityStrict();
this._sectionStart--; //include the current character in the section
}
} else {
this._parseLegacyEntity();
this._sectionStart--;
}
this._state = this._baseState;
this._index--;
}
};
// modified version of https://github.com/mathiasbynens/he/blob/master/src/he.js#L94-L119
function decodeCodePoint(codePoint){
var output = "";
if((codePoint >= 0xD800 && codePoint <= 0xDFFF) || codePoint > 0x10FFFF){
return "\uFFFD";
}
if(codePoint in decodeMap){
codePoint = decodeMap[codePoint];
}
if(codePoint > 0xFFFF){
codePoint -= 0x10000;
output += String.fromCharCode(codePoint >>> 10 & 0x3FF | 0xD800);
codePoint = 0xDC00 | codePoint & 0x3FF;
}
output += String.fromCharCode(codePoint);
return output;
}
Tokenizer.prototype._decodeNumericEntity = function(offset, base){
var sectionStart = this._sectionStart + offset;
if(sectionStart !== this._index){
//parse entity
var entity = this._buffer.substring(sectionStart, this._index);
var parsed = parseInt(entity, base);
if(parsed === parsed){ //not NaN (TODO: when can this happen?)
this._emitPartial(decodeCodePoint(parsed));
this._sectionStart = this._index;
}
}
this._state = this._baseState;
};
Tokenizer.prototype._stateInNumericEntity = function(c){
if(c === ";"){
this._decodeNumericEntity(2, 10);
this._sectionStart++;
} else if(c < "0" || c > "9"){
if(!this._xmlMode){
this._decodeNumericEntity(2, 10);
} else {
this._state = this._baseState;
}
this._index--;
}
};
Tokenizer.prototype._stateInHexEntity = function(c){
if(c === ";"){
this._decodeNumericEntity(3, 16);
this._sectionStart++;
} else if((c < "a" || c > "f") && (c < "A" || c > "F") && (c < "0" || c > "9")){
if(!this._xmlMode){
this._decodeNumericEntity(3, 16);
} else {
this._state = this._baseState;
}
this._index--;
}
};
Tokenizer.prototype._cleanup = function () {
if(this._sectionStart < 0){
this._buffer = "";
this._index = 0;
} else {
if(this._state === TEXT){
if(this._sectionStart !== this._index){
this._cbs.ontext(this._buffer.substr(this._sectionStart));
}
this._buffer = "";
this._index = 0;
} else if(this._sectionStart === this._index){
//the section just started
this._buffer = "";
this._index = 0;
} else {
//remove everything unnecessary
this._buffer = this._buffer.substr(this._sectionStart);
this._index -= this._sectionStart;
}
this._sectionStart = 0;
}
};
//TODO make events conditional
Tokenizer.prototype.write = function(chunk){
this._buffer += chunk;
while(this._index < this._buffer.length && this._running){
var c = this._buffer.charAt(this._index);
if(this._state === TEXT) {
this._stateText(c);
} else if(this._state === BEFORE_TAG_NAME){
this._stateBeforeTagName(c);
} else if(this._state === IN_TAG_NAME) {
this._stateInTagName(c);
} else if(this._state === BEFORE_CLOSING_TAG_NAME){
this._stateBeforeCloseingTagName(c);
} else if(this._state === IN_CLOSING_TAG_NAME){
this._stateInCloseingTagName(c);
} else if(this._state === AFTER_CLOSING_TAG_NAME){
this._stateAfterCloseingTagName(c);
} else if(this._state === IN_SELF_CLOSING_TAG){
this._stateInSelfClosingTag(c);
}
/*
* attributes
*/
else if(this._state === BEFORE_ATTRIBUTE_NAME){
this._stateBeforeAttributeName(c);
} else if(this._state === IN_ATTRIBUTE_NAME){
this._stateInAttributeName(c);
} else if(this._state === AFTER_ATTRIBUTE_NAME){
this._stateAfterAttributeName(c);
} else if(this._state === BEFORE_ATTRIBUTE_VALUE){
this._stateBeforeAttributeValue(c);
} else if(this._state === IN_ATTRIBUTE_VALUE_DQ){
this._stateInAttributeValueDoubleQuotes(c);
} else if(this._state === IN_ATTRIBUTE_VALUE_SQ){
this._stateInAttributeValueSingleQuotes(c);
} else if(this._state === IN_ATTRIBUTE_VALUE_NQ){
this._stateInAttributeValueNoQuotes(c);
}
/*
* declarations
*/
else if(this._state === BEFORE_DECLARATION){
this._stateBeforeDeclaration(c);
} else if(this._state === IN_DECLARATION){
this._stateInDeclaration(c);
}
/*
* processing instructions
*/
else if(this._state === IN_PROCESSING_INSTRUCTION){
this._stateInProcessingInstruction(c);
}
/*
* comments
*/
else if(this._state === BEFORE_COMMENT){
this._stateBeforeComment(c);
} else if(this._state === IN_COMMENT){
this._stateInComment(c);
} else if(this._state === AFTER_COMMENT_1){
this._stateAfterComment1(c);
} else if(this._state === AFTER_COMMENT_2){
this._stateAfterComment2(c);
}
/*
* cdata
*/
else if(this._state === BEFORE_CDATA_1){
this._stateBeforeCdata1(c);
} else if(this._state === BEFORE_CDATA_2){
this._stateBeforeCdata2(c);
} else if(this._state === BEFORE_CDATA_3){
this._stateBeforeCdata3(c);
} else if(this._state === BEFORE_CDATA_4){
this._stateBeforeCdata4(c);
} else if(this._state === BEFORE_CDATA_5){
this._stateBeforeCdata5(c);
} else if(this._state === BEFORE_CDATA_6){
this._stateBeforeCdata6(c);
} else if(this._state === IN_CDATA){
this._stateInCdata(c);
} else if(this._state === AFTER_CDATA_1){
this._stateAfterCdata1(c);
} else if(this._state === AFTER_CDATA_2){
this._stateAfterCdata2(c);
}
/*
* special tags
*/
else if(this._state === BEFORE_SPECIAL){
this._stateBeforeSpecial(c);
} else if(this._state === BEFORE_SPECIAL_END){
this._stateBeforeSpecialEnd(c);
}
/*
* script
*/
else if(this._state === BEFORE_SCRIPT_1){
this._stateBeforeScript1(c);
} else if(this._state === BEFORE_SCRIPT_2){
this._stateBeforeScript2(c);
} else if(this._state === BEFORE_SCRIPT_3){
this._stateBeforeScript3(c);
} else if(this._state === BEFORE_SCRIPT_4){
this._stateBeforeScript4(c);
} else if(this._state === BEFORE_SCRIPT_5){
this._stateBeforeScript5(c);
}
else if(this._state === AFTER_SCRIPT_1){
this._stateAfterScript1(c);
} else if(this._state === AFTER_SCRIPT_2){
this._stateAfterScript2(c);
} else if(this._state === AFTER_SCRIPT_3){
this._stateAfterScript3(c);
} else if(this._state === AFTER_SCRIPT_4){
this._stateAfterScript4(c);
} else if(this._state === AFTER_SCRIPT_5){
this._stateAfterScript5(c);
}
/*
* style
*/
else if(this._state === BEFORE_STYLE_1){
this._stateBeforeStyle1(c);
} else if(this._state === BEFORE_STYLE_2){
this._stateBeforeStyle2(c);
} else if(this._state === BEFORE_STYLE_3){
this._stateBeforeStyle3(c);
} else if(this._state === BEFORE_STYLE_4){
this._stateBeforeStyle4(c);
}
else if(this._state === AFTER_STYLE_1){
this._stateAfterStyle1(c);
} else if(this._state === AFTER_STYLE_2){
this._stateAfterStyle2(c);
} else if(this._state === AFTER_STYLE_3){
this._stateAfterStyle3(c);
} else if(this._state === AFTER_STYLE_4){
this._stateAfterStyle4(c);
}
/*
* entities
*/
else if(this._state === BEFORE_ENTITY){
this._stateBeforeEntity(c);
} else if(this._state === BEFORE_NUMERIC_ENTITY){
this._stateBeforeNumericEntity(c);
} else if(this._state === IN_NAMED_ENTITY){
this._stateInNamedEntity(c);
} else if(this._state === IN_NUMERIC_ENTITY){
this._stateInNumericEntity(c);
} else if(this._state === IN_HEX_ENTITY){
this._stateInHexEntity(c);
}
else {
this._cbs.onerror(Error("unknown _state"), this._state);
}
this._index++;
}
this._cleanup();
};
Tokenizer.prototype.pause = function(){
this._running = false;
};
Tokenizer.prototype.resume = function(){
this._running = true;
};
Tokenizer.prototype.end = function(chunk){
if(chunk) this.write(chunk);
//if there is remaining data, emit it in a reasonable way
if(this._sectionStart < this._index){
this._handleTrailingData();
}
this._cbs.onend();
};
Tokenizer.prototype._handleTrailingData = function(){
var data = this._buffer.substr(this._sectionStart);
if(this._state === IN_CDATA || this._state === AFTER_CDATA_1 || this._state === AFTER_CDATA_2){
this._cbs.oncdata(data);
} else if(this._state === IN_COMMENT || this._state === AFTER_COMMENT_1 || this._state === AFTER_COMMENT_2){
this._cbs.oncomment(data);
} else if(this._state === IN_TAG_NAME){
this._cbs.onopentagname(data);
} else if(this._state === BEFORE_ATTRIBUTE_NAME || this._state === BEFORE_ATTRIBUTE_VALUE || this._state === AFTER_ATTRIBUTE_NAME){
this._cbs.onopentagend();
} else if(this._state === IN_ATTRIBUTE_NAME){
this._cbs.onattribname(data);
} else if(this._state === IN_ATTRIBUTE_VALUE_SQ || this._state === IN_ATTRIBUTE_VALUE_DQ || this._state === IN_ATTRIBUTE_VALUE_NQ){
this._cbs.onattribdata(data);
this._cbs.onattribend();
} else if(this._state === IN_CLOSING_TAG_NAME){
this._cbs.onclosetag(data);
} else if(this._state === IN_NAMED_ENTITY && !this._xmlMode){
this._parseLegacyEntity();
if(--this._sectionStart < this._index){
this._state = this._baseState;
this._handleTrailingData();
}
} else if(this._state === IN_NUMERIC_ENTITY && !this._xmlMode){
this._decodeNumericEntity(2, 10);
if(this._sectionStart < this._index){
this._state = this._baseState;
this._handleTrailingData();
}
} else if(this._state === IN_HEX_ENTITY && !this._xmlMode){
this._decodeNumericEntity(3, 16);
if(this._sectionStart < this._index){
this._state = this._baseState;
this._handleTrailingData();
}
} else {
this._cbs.ontext(data);
}
};
Tokenizer.prototype.reset = function(){
Tokenizer.call(this, {xmlMode: this._xmlMode, decodeEntities: this._decodeEntities}, this._cbs);
};
Tokenizer.prototype._getSection = function(){
return this._buffer.substring(this._sectionStart, this._index);
};
Tokenizer.prototype._emitToken = function(name){
this._cbs[name](this._getSection());
this._sectionStart = -1;
};
Tokenizer.prototype._emitPartial = function(value){
if(this._baseState !== TEXT){
this._cbs.onattribdata(value); //TODO implement the new event
} else {
this._cbs.ontext(value);
}
};

View File

@@ -0,0 +1,21 @@
module.exports = Stream;
var Parser = require("./Parser.js"),
WritableStream = require("stream").Writable || require("readable-stream").Writable;
function Stream(cbs, options){
var parser = this._parser = new Parser(cbs, options);
WritableStream.call(this, {decodeStrings: false});
this.once("finish", function(){
parser.end();
});
}
require("util").inherits(Stream, WritableStream);
WritableStream.prototype._write = function(chunk, encoding, cb){
this._parser.write(chunk);
cb();
};

View File

@@ -0,0 +1 @@
{"0":"\uFFFD","128":"\u20AC","130":"\u201A","131":"\u0192","132":"\u201E","133":"\u2026","134":"\u2020","135":"\u2021","136":"\u02C6","137":"\u2030","138":"\u0160","139":"\u2039","140":"\u0152","142":"\u017D","145":"\u2018","146":"\u2019","147":"\u201C","148":"\u201D","149":"\u2022","150":"\u2013","151":"\u2014","152":"\u02DC","153":"\u2122","154":"\u0161","155":"\u203A","156":"\u0153","158":"\u017E","159":"\u0178"}

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1 @@
{"Aacute":"\u00C1","aacute":"\u00E1","Acirc":"\u00C2","acirc":"\u00E2","acute":"\u00B4","AElig":"\u00C6","aelig":"\u00E6","Agrave":"\u00C0","agrave":"\u00E0","amp":"&","AMP":"&","Aring":"\u00C5","aring":"\u00E5","Atilde":"\u00C3","atilde":"\u00E3","Auml":"\u00C4","auml":"\u00E4","brvbar":"\u00A6","Ccedil":"\u00C7","ccedil":"\u00E7","cedil":"\u00B8","cent":"\u00A2","copy":"\u00A9","COPY":"\u00A9","curren":"\u00A4","deg":"\u00B0","divide":"\u00F7","Eacute":"\u00C9","eacute":"\u00E9","Ecirc":"\u00CA","ecirc":"\u00EA","Egrave":"\u00C8","egrave":"\u00E8","ETH":"\u00D0","eth":"\u00F0","Euml":"\u00CB","euml":"\u00EB","frac12":"\u00BD","frac14":"\u00BC","frac34":"\u00BE","gt":">","GT":">","Iacute":"\u00CD","iacute":"\u00ED","Icirc":"\u00CE","icirc":"\u00EE","iexcl":"\u00A1","Igrave":"\u00CC","igrave":"\u00EC","iquest":"\u00BF","Iuml":"\u00CF","iuml":"\u00EF","laquo":"\u00AB","lt":"<","LT":"<","macr":"\u00AF","micro":"\u00B5","middot":"\u00B7","nbsp":"\u00A0","not":"\u00AC","Ntilde":"\u00D1","ntilde":"\u00F1","Oacute":"\u00D3","oacute":"\u00F3","Ocirc":"\u00D4","ocirc":"\u00F4","Ograve":"\u00D2","ograve":"\u00F2","ordf":"\u00AA","ordm":"\u00BA","Oslash":"\u00D8","oslash":"\u00F8","Otilde":"\u00D5","otilde":"\u00F5","Ouml":"\u00D6","ouml":"\u00F6","para":"\u00B6","plusmn":"\u00B1","pound":"\u00A3","quot":"\"","QUOT":"\"","raquo":"\u00BB","reg":"\u00AE","REG":"\u00AE","sect":"\u00A7","shy":"\u00AD","sup1":"\u00B9","sup2":"\u00B2","sup3":"\u00B3","szlig":"\u00DF","THORN":"\u00DE","thorn":"\u00FE","times":"\u00D7","Uacute":"\u00DA","uacute":"\u00FA","Ucirc":"\u00DB","ucirc":"\u00FB","Ugrave":"\u00D9","ugrave":"\u00F9","uml":"\u00A8","Uuml":"\u00DC","uuml":"\u00FC","Yacute":"\u00DD","yacute":"\u00FD","yen":"\u00A5","yuml":"\u00FF"}

View File

@@ -0,0 +1 @@
{"amp":"&","apos":"'","gt":">","lt":"<","quot":"\""}

View File

@@ -0,0 +1,70 @@
var Parser = require("./Parser.js"),
DomHandler = require("domhandler");
function defineProp(name, value){
delete module.exports[name];
module.exports[name] = value;
return value;
}
module.exports = {
Parser: Parser,
Tokenizer: require("./Tokenizer.js"),
ElementType: require("domelementtype"),
DomHandler: DomHandler,
get FeedHandler(){
return defineProp("FeedHandler", require("./FeedHandler.js"));
},
get Stream(){
return defineProp("Stream", require("./Stream.js"));
},
get WritableStream(){
return defineProp("WritableStream", require("./WritableStream.js"));
},
get ProxyHandler(){
return defineProp("ProxyHandler", require("./ProxyHandler.js"));
},
get DomUtils(){
return defineProp("DomUtils", require("domutils"));
},
get CollectingHandler(){
return defineProp("CollectingHandler", require("./CollectingHandler.js"));
},
// For legacy support
DefaultHandler: DomHandler,
get RssHandler(){
return defineProp("RssHandler", this.FeedHandler);
},
//helper methods
parseDOM: function(data, options) {
var handler = new DomHandler(options);
var parser = new Parser(handler, options);
parser.end(data);
return handler.dom;
},
parseFeed: function(feed, options){
var handler = new module.exports.FeedHandler();
var parser = new Parser(handler);
parser.end(feed);
return handler.dom;
},
createDomStream: function(cb, options, elementCb){
var handler = new DomHandler(cb, options, elementCb);
return new Parser(handler, options);
},
// List of all events that the parser emits
EVENTS: { /* Format: eventname: number of arguments */
attribute: 2,
cdatastart: 0,
cdataend: 0,
text: 1,
processinginstruction: 2,
comment: 1,
commentend: 0,
closetag: 1,
opentag: 2,
opentagname: 1,
error: 1,
end: 0
}
};

View File

@@ -0,0 +1,11 @@
Copyright (c) Felix Böhm
All rights reserved.
Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
THIS IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS,
EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

View File

@@ -0,0 +1,318 @@
var ElementType = require("domelementtype"),
DomUtils = module.exports;
var isTag = DomUtils.isTag = ElementType.isTag;
function getChildren(elem){
return elem.children;
}
function getParent(elem){
return elem.parent;
}
function getSiblings(elem){
var parent = getParent(elem);
return parent ? getChildren(parent) : [elem];
}
function getAttributeValue(elem, name){
return elem.attribs && elem.attribs[name];
}
function hasAttrib(elem, name){
return hasOwnProperty.call(elem.attribs, name);
}
function getName(elem){
return elem.name;
}
DomUtils.getChildren = getChildren;
DomUtils.getParent = getParent;
DomUtils.getAttributeValue = getAttributeValue;
DomUtils.hasAttrib = hasAttrib;
DomUtils.getName = getName;
DomUtils.getSiblings = getSiblings;
function find(test, arr, recurse, limit){
var result = [], childs;
for(var i = 0, j = arr.length; i < j; i++){
if(test(arr[i])){
result.push(arr[i]);
if(--limit <= 0) break;
}
childs = getChildren(arr[i]);
if(recurse && childs && childs.length > 0){
childs = find(test, childs, recurse, limit);
result = result.concat(childs);
limit -= childs.length;
if(limit <= 0) break;
}
}
return result;
}
function findOneChild(test, arr){
for(var i = 0, l = arr.length; i < l; i++){
if(test(arr[i])) return arr[i];
}
return null;
}
function findOne(test, arr){
var elem = null;
for(var i = 0, l = arr.length; i < l && !elem; i++){
if(test(arr[i])){
elem = arr[i];
} else if(arr[i].children && arr[i].children.length > 0){
elem = findOne(test, arr[i].children);
}
}
return elem;
}
DomUtils.findOne = findOne;
function findAll(test, elems){
var result = [];
for(var i = 0, j = elems.length; i < j; i++){
if(test(elems[i])) result.push(elems[i]);
var childs = getChildren(elems[i]);
if(childs && childs.length){
result = result.concat(findAll(test, childs));
}
}
return result;
}
DomUtils.findAll = findAll;
function filter(test, element, recurse, limit){
if(!Array.isArray(element)) element = [element];
if(typeof limit !== "number" || !isFinite(limit)){
if(recurse === false){
return element.filter(test);
} else {
return findAll(test, element);
}
} else if(limit === 1){
if(recurse === false){
element = findOneChild(test, element);
} else {
element = findOne(test, element);
}
return element ? [element] : [];
} else {
return find(test, element, recurse !== false, limit);
}
}
DomUtils.filter = filter;
DomUtils.testElement = function(options, element){
for(var key in options){
if(!options.hasOwnProperty(key));
else if(key === "tag_name"){
if(!isTag(element) || !options.tag_name(element.name)){
return false;
}
} else if(key === "tag_type"){
if(!options.tag_type(element.type)) return false;
} else if(key === "tag_contains"){
if(isTag(element) || !options.tag_contains(element.data)){
return false;
}
} else if(!element.attribs || !options[key](element.attribs[key])){
return false;
}
}
return true;
};
var Checks = {
tag_name: function(name){
if(typeof name === "function"){
return function(elem){ return isTag(elem) && name(elem.name); };
} else if(name === "*"){
return isTag;
} else {
return function(elem){ return isTag(elem) && elem.name === name; };
}
},
tag_type: function(type){
if(typeof type === "function"){
return function(elem){ return type(elem.type); };
} else {
return function(elem){ return elem.type === type; };
}
},
tag_contains: function(data){
if(typeof type === "function"){
return function(elem){ return !isTag(elem) && data(elem.data); };
} else {
return function(elem){ return !isTag(elem) && elem.data === data; };
}
}
};
function getAttribCheck(attrib, value){
if(typeof value === "function"){
return function(elem){ return elem.attribs && value(elem.attribs[attrib]); };
} else {
return function(elem){ return elem.attribs && elem.attribs[attrib] === value; };
}
}
DomUtils.getElements = function(options, element, recurse, limit){
var funcs = [];
for(var key in options){
if(options.hasOwnProperty(key)){
if(key in Checks) funcs.push(Checks[key](options[key]));
else funcs.push(getAttribCheck(key, options[key]));
}
}
if(funcs.length === 0) return [];
if(funcs.length === 1) return filter(funcs[0], element, recurse, limit);
return filter(
function(elem){
return funcs.some(function(func){ return func(elem); });
},
element, recurse, limit
);
};
DomUtils.getElementById = function(id, element, recurse){
if(!Array.isArray(element)) element = [element];
return findOne(getAttribCheck("id", id), element, recurse !== false);
};
DomUtils.getElementsByTagName = function(name, element, recurse, limit){
return filter(Checks.tag_name(name), element, recurse, limit);
};
DomUtils.getElementsByTagType = function(type, element, recurse, limit){
return filter(Checks.tag_type(type), element, recurse, limit);
};
DomUtils.removeElement = function(elem){
if(elem.prev) elem.prev.next = elem.next;
if(elem.next) elem.next.prev = elem.prev;
if(elem.parent){
var childs = elem.parent.children;
childs.splice(childs.lastIndexOf(elem), 1);
}
};
DomUtils.replaceElement = function(elem, replacement){
if(elem.prev){
elem.prev.next = replacement;
replacement.prev = elem.prev;
}
if(elem.next){
elem.next.prev = replacement;
replacement.next = elem.next;
}
if(elem.parent){
var childs = elem.parent.children;
childs.splice(childs.lastIndexOf(elem), 1, replacement);
replacement.parent = elem.parent;
}
};
DomUtils.getInnerHTML = function(elem){
if(!elem.children) return "";
var childs = elem.children,
childNum = childs.length,
ret = "";
for(var i = 0; i < childNum; i++){
ret += DomUtils.getOuterHTML(childs[i]);
}
return ret;
};
//boolean attributes without a value (taken from MatthewMueller/cheerio)
var booleanAttribs = {
__proto__: null,
async: true,
autofocus: true,
autoplay: true,
checked: true,
controls: true,
defer: true,
disabled: true,
hidden: true,
loop: true,
multiple: true,
open: true,
readonly: true,
required: true,
scoped: true,
selected: true,
"/": true //TODO when is this required?
};
var emptyTags = {
__proto__: null,
area: true,
base: true,
basefont: true,
br: true,
col: true,
frame: true,
hr: true,
img: true,
input: true,
isindex: true,
link: true,
meta: true,
param: true,
embed: true
};
DomUtils.getOuterHTML = function(elem){
var type = elem.type;
if(type === ElementType.Text) return elem.data;
if(type === ElementType.Comment) return "<!--" + elem.data + "-->";
if(type === ElementType.Directive) return "<" + elem.data + ">";
if(type === ElementType.CDATA) return "<!CDATA " + DomUtils.getInnerHTML(elem) + "]]>";
var ret = "<" + elem.name;
if("attribs" in elem){
for(var attr in elem.attribs){
if(elem.attribs.hasOwnProperty(attr)){
ret += " " + attr;
var value = elem.attribs[attr];
if(!value){
if( !(attr in booleanAttribs) ){
ret += '=""';
}
} else {
ret += '="' + value + '"';
}
}
}
}
if (elem.name in emptyTags && elem.children.length === 0) {
return ret + " />";
} else {
return ret + ">" + DomUtils.getInnerHTML(elem) + "</" + elem.name + ">";
}
};
DomUtils.getText = function getText(elem){
if(Array.isArray(elem)) return elem.map(getText).join("");
if(isTag(elem) || elem.type === ElementType.CDATA) return getText(elem.children);
if(elem.type === ElementType.Text) return elem.data;
return "";
};

View File

@@ -0,0 +1,63 @@
{
"_args": [
[
"domutils@1.1.6",
"C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project"
]
],
"_from": "domutils@1.1.6",
"_id": "domutils@1.1.6",
"_inBundle": false,
"_integrity": "sha1-vdw94Jm5ou+sxRxiPyj0FuzFdIU=",
"_location": "/react-scripts/htmlparser2/domutils",
"_phantomChildren": {},
"_requested": {
"type": "version",
"registry": true,
"raw": "domutils@1.1.6",
"name": "domutils",
"escapedName": "domutils",
"rawSpec": "1.1.6",
"saveSpec": null,
"fetchSpec": "1.1.6"
},
"_requiredBy": [
"/react-scripts/htmlparser2"
],
"_resolved": "https://registry.npmjs.org/domutils/-/domutils-1.1.6.tgz",
"_spec": "1.1.6",
"_where": "C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project",
"author": {
"name": "Felix Boehm",
"email": "me@feedic.com"
},
"bugs": {
"url": "https://github.com/FB55/domutils/issues"
},
"dependencies": {
"domelementtype": "1"
},
"description": "utilities for working with htmlparser2's dom",
"devDependencies": {
"domhandler": "2",
"htmlparser2": "2.3"
},
"directories": {
"test": "tests"
},
"homepage": "https://github.com/FB55/domutils#readme",
"keywords": [
"dom",
"htmlparser2"
],
"main": "index.js",
"name": "domutils",
"repository": {
"type": "git",
"url": "git://github.com/FB55/domutils.git"
},
"scripts": {
"test": "node tests/00-runtests.js"
},
"version": "1.1.6"
}

View File

@@ -0,0 +1 @@
utilities for working with htmlparser2's dom

View File

@@ -0,0 +1,64 @@
var fs = require("fs"),
assert = require("assert");
var runCount = 0,
testCount = 0;
function compare(expected, result){
if(typeof expected !== typeof result){
throw Error("types didn't match");
}
if(typeof expected !== "object" || expected === null){
if(expected !== result){
throw Error("result doesn't equal expected");
}
return;
}
for(var prop in expected){
if(!(prop in result)) throw Error("result didn't contain property " + prop);
compare(expected[prop], result[prop]);
}
}
function runTests(test){
//read files, load them, run them
fs.readdirSync(__dirname + test.dir
).map(function(file){
if(file[0] === ".") return false;
if(file.substr(-5) === ".json") return JSON.parse(
fs.readFileSync(__dirname + test.dir + file)
);
return require(__dirname + test.dir + file);
}).forEach(function(file){
if(!file) return;
var second = false;
runCount++;
console.log("Testing:", file.name);
test.test(file, function(err, dom){
assert.ifError(err);
compare(file.expected, dom);
if(second){
runCount--;
testCount++;
}
else second = true;
});
});
console.log("->", test.dir.slice(1, -1), "started");
}
//run all tests
[
"./02-dom_utils.js"
].map(require).forEach(runTests);
//log the results
(function check(){
if(runCount !== 0) return process.nextTick(check);
console.log("Total tests:", testCount);
}());

View File

@@ -0,0 +1,15 @@
//generate a dom
var handler = new (require("domhandler"))();
(new (require("htmlparser2").Parser)(handler)).parseComplete(
Array(21).join("<?xml><tag1 id='asdf'> <script>text</script> <!-- comment --> <tag2> text </tag1>")
);
var dom = handler.dom;
exports.dir = "/DomUtils/";
exports.test = function(test, cb){
cb(null, test.getElements(dom));
cb(null, test.getByFunction(dom));
};

View File

@@ -0,0 +1,56 @@
var DomUtils = require("../..");
exports.name = "Get element by id";
exports.getElements = function(dom){
return DomUtils.getElements({id:"asdf"}, dom, true, 1)[0];
};
exports.getByFunction = function(dom){
return DomUtils.getElementById("asdf", dom, true);
};
exports.expected = {
"type": "tag",
"name": "tag1",
"attribs": {
"id": "asdf"
},
"children": [
{
"data": " ",
"type": "text"
},
{
"type": "script",
"name": "script",
"attribs": {},
"children": [
{
"data": "text",
"type": "text"
}
]
},
{
"data": " ",
"type": "text"
},
{
"data": " comment ",
"type": "comment"
},
{
"data": " ",
"type": "text"
},
{
"type": "tag",
"name": "tag2",
"attribs": {},
"children": [
{
"data": " text ",
"type": "text"
}
]
}
]
};

View File

@@ -0,0 +1,23 @@
var DomUtils = require("../..");
exports.name = "Get elements by tagName";
exports.getElements = function(dom){
return DomUtils.getElements({tag_name:"tag2"}, dom, true);
};
exports.getByFunction = function(dom){
return DomUtils.getElementsByTagName("tag2", dom, true);
};
exports.expected = [];
for(var i = 0; i < 20; i++) exports.expected.push(
{
"type": "tag",
"name": "tag2",
"attribs": {},
"children": [
{
"data": " text ",
"type": "text"
}
]
}
);

View File

@@ -0,0 +1,23 @@
var DomUtils = require("../..");
exports.name = "Get elements by type";
exports.getElements = function(dom){
return DomUtils.getElements({tag_type:"script"}, dom, true);
};
exports.getByFunction = function(dom){
return DomUtils.getElementsByTagType("script", dom, true);
};
exports.expected = [];
for(var i = 0; i < 20; i++) exports.expected.push(
{
"type": "script",
"name": "script",
"attribs": {},
"children": [
{
"data": "text",
"type": "text"
}
]
}
);

View File

@@ -0,0 +1,10 @@
var DomUtils = require("../..");
exports.name = "Get outer HTML";
exports.getElements = function(dom){
return '<tag1 id="asdf"> <script>text</script> <!-- comment --> <tag2> text </tag2></tag1>';
};
exports.getByFunction = function(dom){
return DomUtils.getOuterHTML(DomUtils.getElementById("asdf", dom, true));
};
exports.expected = '<tag1 id="asdf"> <script>text</script> <!-- comment --> <tag2> text </tag2></tag1>';

View File

@@ -0,0 +1,10 @@
var DomUtils = require("../..");
exports.name = "Get inner HTML";
exports.getElements = function(dom){
return ' <script>text</script> <!-- comment --> <tag2> text </tag2>';
};
exports.getByFunction = function(dom){
return DomUtils.getInnerHTML(DomUtils.getElementById("asdf", dom, true));
};
exports.expected = ' <script>text</script> <!-- comment --> <tag2> text </tag2>';

View File

@@ -0,0 +1,54 @@
# isarray
`Array#isArray` for older browsers.
## Usage
```js
var isArray = require('isarray');
console.log(isArray([])); // => true
console.log(isArray({})); // => false
```
## Installation
With [npm](http://npmjs.org) do
```bash
$ npm install isarray
```
Then bundle for the browser with
[browserify](https://github.com/substack/browserify).
With [component](http://component.io) do
```bash
$ component install juliangruber/isarray
```
## License
(MIT)
Copyright (c) 2013 Julian Gruber &lt;julian@juliangruber.com&gt;
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
of the Software, and to permit persons to whom the Software is furnished to do
so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

View File

@@ -0,0 +1,209 @@
/**
* Require the given path.
*
* @param {String} path
* @return {Object} exports
* @api public
*/
function require(path, parent, orig) {
var resolved = require.resolve(path);
// lookup failed
if (null == resolved) {
orig = orig || path;
parent = parent || 'root';
var err = new Error('Failed to require "' + orig + '" from "' + parent + '"');
err.path = orig;
err.parent = parent;
err.require = true;
throw err;
}
var module = require.modules[resolved];
// perform real require()
// by invoking the module's
// registered function
if (!module.exports) {
module.exports = {};
module.client = module.component = true;
module.call(this, module.exports, require.relative(resolved), module);
}
return module.exports;
}
/**
* Registered modules.
*/
require.modules = {};
/**
* Registered aliases.
*/
require.aliases = {};
/**
* Resolve `path`.
*
* Lookup:
*
* - PATH/index.js
* - PATH.js
* - PATH
*
* @param {String} path
* @return {String} path or null
* @api private
*/
require.resolve = function(path) {
if (path.charAt(0) === '/') path = path.slice(1);
var index = path + '/index.js';
var paths = [
path,
path + '.js',
path + '.json',
path + '/index.js',
path + '/index.json'
];
for (var i = 0; i < paths.length; i++) {
var path = paths[i];
if (require.modules.hasOwnProperty(path)) return path;
}
if (require.aliases.hasOwnProperty(index)) {
return require.aliases[index];
}
};
/**
* Normalize `path` relative to the current path.
*
* @param {String} curr
* @param {String} path
* @return {String}
* @api private
*/
require.normalize = function(curr, path) {
var segs = [];
if ('.' != path.charAt(0)) return path;
curr = curr.split('/');
path = path.split('/');
for (var i = 0; i < path.length; ++i) {
if ('..' == path[i]) {
curr.pop();
} else if ('.' != path[i] && '' != path[i]) {
segs.push(path[i]);
}
}
return curr.concat(segs).join('/');
};
/**
* Register module at `path` with callback `definition`.
*
* @param {String} path
* @param {Function} definition
* @api private
*/
require.register = function(path, definition) {
require.modules[path] = definition;
};
/**
* Alias a module definition.
*
* @param {String} from
* @param {String} to
* @api private
*/
require.alias = function(from, to) {
if (!require.modules.hasOwnProperty(from)) {
throw new Error('Failed to alias "' + from + '", it does not exist');
}
require.aliases[to] = from;
};
/**
* Return a require function relative to the `parent` path.
*
* @param {String} parent
* @return {Function}
* @api private
*/
require.relative = function(parent) {
var p = require.normalize(parent, '..');
/**
* lastIndexOf helper.
*/
function lastIndexOf(arr, obj) {
var i = arr.length;
while (i--) {
if (arr[i] === obj) return i;
}
return -1;
}
/**
* The relative require() itself.
*/
function localRequire(path) {
var resolved = localRequire.resolve(path);
return require(resolved, parent, path);
}
/**
* Resolve relative to the parent.
*/
localRequire.resolve = function(path) {
var c = path.charAt(0);
if ('/' == c) return path.slice(1);
if ('.' == c) return require.normalize(p, path);
// resolve deps by returning
// the dep in the nearest "deps"
// directory
var segs = parent.split('/');
var i = lastIndexOf(segs, 'deps') + 1;
if (!i) i = 0;
path = segs.slice(0, i + 1).join('/') + '/deps/' + path;
return path;
};
/**
* Check if module is defined at `path`.
*/
localRequire.exists = function(path) {
return require.modules.hasOwnProperty(localRequire.resolve(path));
};
return localRequire;
};
require.register("isarray/index.js", function(exports, require, module){
module.exports = Array.isArray || function (arr) {
return Object.prototype.toString.call(arr) == '[object Array]';
};
});
require.alias("isarray/index.js", "isarray/index.js");

View File

@@ -0,0 +1,19 @@
{
"name" : "isarray",
"description" : "Array#isArray for older browsers",
"version" : "0.0.1",
"repository" : "juliangruber/isarray",
"homepage": "https://github.com/juliangruber/isarray",
"main" : "index.js",
"scripts" : [
"index.js"
],
"dependencies" : {},
"keywords": ["browser","isarray","array"],
"author": {
"name": "Julian Gruber",
"email": "mail@juliangruber.com",
"url": "http://juliangruber.com"
},
"license": "MIT"
}

View File

@@ -0,0 +1,3 @@
module.exports = Array.isArray || function (arr) {
return Object.prototype.toString.call(arr) == '[object Array]';
};

View File

@@ -0,0 +1,60 @@
{
"_args": [
[
"isarray@0.0.1",
"C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project"
]
],
"_from": "isarray@0.0.1",
"_id": "isarray@0.0.1",
"_inBundle": false,
"_integrity": "sha1-ihis/Kmo9Bd+Cav8YDiTmwXR7t8=",
"_location": "/react-scripts/htmlparser2/isarray",
"_phantomChildren": {},
"_requested": {
"type": "version",
"registry": true,
"raw": "isarray@0.0.1",
"name": "isarray",
"escapedName": "isarray",
"rawSpec": "0.0.1",
"saveSpec": null,
"fetchSpec": "0.0.1"
},
"_requiredBy": [
"/react-scripts/htmlparser2/readable-stream"
],
"_resolved": "https://registry.npmjs.org/isarray/-/isarray-0.0.1.tgz",
"_spec": "0.0.1",
"_where": "C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project",
"author": {
"name": "Julian Gruber",
"email": "mail@juliangruber.com",
"url": "http://juliangruber.com"
},
"bugs": {
"url": "https://github.com/juliangruber/isarray/issues"
},
"dependencies": {},
"description": "Array#isArray for older browsers",
"devDependencies": {
"tap": "*"
},
"homepage": "https://github.com/juliangruber/isarray",
"keywords": [
"browser",
"isarray",
"array"
],
"license": "MIT",
"main": "index.js",
"name": "isarray",
"repository": {
"type": "git",
"url": "git://github.com/juliangruber/isarray.git"
},
"scripts": {
"test": "tap test/*.js"
},
"version": "0.0.1"
}

View File

@@ -0,0 +1,5 @@
build/
test/
examples/
fs.js
zlib.js

View File

@@ -0,0 +1,18 @@
Copyright Joyent, Inc. and other Node contributors. All rights reserved.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to
deal in the Software without restriction, including without limitation the
rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
IN THE SOFTWARE.

View File

@@ -0,0 +1,15 @@
# readable-stream
***Node-core streams for userland***
[![NPM](https://nodei.co/npm/readable-stream.png?downloads=true&downloadRank=true)](https://nodei.co/npm/readable-stream/)
[![NPM](https://nodei.co/npm-dl/readable-stream.png?&months=6&height=3)](https://nodei.co/npm/readable-stream/)
This package is a mirror of the Streams2 and Streams3 implementations in Node-core.
If you want to guarantee a stable streams base, regardless of what version of Node you, or the users of your libraries are using, use **readable-stream** *only* and avoid the *"stream"* module in Node-core.
**readable-stream** comes in two major versions, v1.0.x and v1.1.x. The former tracks the Streams2 implementation in Node 0.10, including bug-fixes and minor improvements as they are added. The latter tracks Streams3 as it develops in Node 0.11; we will likely see a v1.2.x branch for Node 0.12.
**readable-stream** uses proper patch-level versioning so if you pin to `"~1.0.0"` youll get the latest Node 0.10 Streams2 implementation, including any fixes and minor non-breaking improvements. The patch-level versions of 1.0.x and 1.1.x should mirror the patch-level versions of Node-core releases. You should prefer the **1.0.x** releases for now and when youre ready to start using Streams3, pin to `"~1.1.0"`

View File

@@ -0,0 +1 @@
module.exports = require("./lib/_stream_duplex.js")

View File

@@ -0,0 +1,89 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
// a duplex stream is just a stream that is both readable and writable.
// Since JS doesn't have multiple prototypal inheritance, this class
// prototypally inherits from Readable, and then parasitically from
// Writable.
module.exports = Duplex;
/*<replacement>*/
var objectKeys = Object.keys || function (obj) {
var keys = [];
for (var key in obj) keys.push(key);
return keys;
}
/*</replacement>*/
/*<replacement>*/
var util = require('core-util-is');
util.inherits = require('inherits');
/*</replacement>*/
var Readable = require('./_stream_readable');
var Writable = require('./_stream_writable');
util.inherits(Duplex, Readable);
forEach(objectKeys(Writable.prototype), function(method) {
if (!Duplex.prototype[method])
Duplex.prototype[method] = Writable.prototype[method];
});
function Duplex(options) {
if (!(this instanceof Duplex))
return new Duplex(options);
Readable.call(this, options);
Writable.call(this, options);
if (options && options.readable === false)
this.readable = false;
if (options && options.writable === false)
this.writable = false;
this.allowHalfOpen = true;
if (options && options.allowHalfOpen === false)
this.allowHalfOpen = false;
this.once('end', onend);
}
// the no-half-open enforcer
function onend() {
// if we allow half-open state, or if the writable side ended,
// then we're ok.
if (this.allowHalfOpen || this._writableState.ended)
return;
// no more data can be written.
// But allow more writes to happen in this tick.
process.nextTick(this.end.bind(this));
}
function forEach (xs, f) {
for (var i = 0, l = xs.length; i < l; i++) {
f(xs[i], i);
}
}

View File

@@ -0,0 +1,46 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
// a passthrough stream.
// basically just the most minimal sort of Transform stream.
// Every written chunk gets output as-is.
module.exports = PassThrough;
var Transform = require('./_stream_transform');
/*<replacement>*/
var util = require('core-util-is');
util.inherits = require('inherits');
/*</replacement>*/
util.inherits(PassThrough, Transform);
function PassThrough(options) {
if (!(this instanceof PassThrough))
return new PassThrough(options);
Transform.call(this, options);
}
PassThrough.prototype._transform = function(chunk, encoding, cb) {
cb(null, chunk);
};

View File

@@ -0,0 +1,982 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
module.exports = Readable;
/*<replacement>*/
var isArray = require('isarray');
/*</replacement>*/
/*<replacement>*/
var Buffer = require('buffer').Buffer;
/*</replacement>*/
Readable.ReadableState = ReadableState;
var EE = require('events').EventEmitter;
/*<replacement>*/
if (!EE.listenerCount) EE.listenerCount = function(emitter, type) {
return emitter.listeners(type).length;
};
/*</replacement>*/
var Stream = require('stream');
/*<replacement>*/
var util = require('core-util-is');
util.inherits = require('inherits');
/*</replacement>*/
var StringDecoder;
util.inherits(Readable, Stream);
function ReadableState(options, stream) {
options = options || {};
// the point at which it stops calling _read() to fill the buffer
// Note: 0 is a valid value, means "don't call _read preemptively ever"
var hwm = options.highWaterMark;
this.highWaterMark = (hwm || hwm === 0) ? hwm : 16 * 1024;
// cast to ints.
this.highWaterMark = ~~this.highWaterMark;
this.buffer = [];
this.length = 0;
this.pipes = null;
this.pipesCount = 0;
this.flowing = false;
this.ended = false;
this.endEmitted = false;
this.reading = false;
// In streams that never have any data, and do push(null) right away,
// the consumer can miss the 'end' event if they do some I/O before
// consuming the stream. So, we don't emit('end') until some reading
// happens.
this.calledRead = false;
// a flag to be able to tell if the onwrite cb is called immediately,
// or on a later tick. We set this to true at first, becuase any
// actions that shouldn't happen until "later" should generally also
// not happen before the first write call.
this.sync = true;
// whenever we return null, then we set a flag to say
// that we're awaiting a 'readable' event emission.
this.needReadable = false;
this.emittedReadable = false;
this.readableListening = false;
// object stream flag. Used to make read(n) ignore n and to
// make all the buffer merging and length checks go away
this.objectMode = !!options.objectMode;
// Crypto is kind of old and crusty. Historically, its default string
// encoding is 'binary' so we have to make this configurable.
// Everything else in the universe uses 'utf8', though.
this.defaultEncoding = options.defaultEncoding || 'utf8';
// when piping, we only care about 'readable' events that happen
// after read()ing all the bytes and not getting any pushback.
this.ranOut = false;
// the number of writers that are awaiting a drain event in .pipe()s
this.awaitDrain = 0;
// if true, a maybeReadMore has been scheduled
this.readingMore = false;
this.decoder = null;
this.encoding = null;
if (options.encoding) {
if (!StringDecoder)
StringDecoder = require('string_decoder/').StringDecoder;
this.decoder = new StringDecoder(options.encoding);
this.encoding = options.encoding;
}
}
function Readable(options) {
if (!(this instanceof Readable))
return new Readable(options);
this._readableState = new ReadableState(options, this);
// legacy
this.readable = true;
Stream.call(this);
}
// Manually shove something into the read() buffer.
// This returns true if the highWaterMark has not been hit yet,
// similar to how Writable.write() returns true if you should
// write() some more.
Readable.prototype.push = function(chunk, encoding) {
var state = this._readableState;
if (typeof chunk === 'string' && !state.objectMode) {
encoding = encoding || state.defaultEncoding;
if (encoding !== state.encoding) {
chunk = new Buffer(chunk, encoding);
encoding = '';
}
}
return readableAddChunk(this, state, chunk, encoding, false);
};
// Unshift should *always* be something directly out of read()
Readable.prototype.unshift = function(chunk) {
var state = this._readableState;
return readableAddChunk(this, state, chunk, '', true);
};
function readableAddChunk(stream, state, chunk, encoding, addToFront) {
var er = chunkInvalid(state, chunk);
if (er) {
stream.emit('error', er);
} else if (chunk === null || chunk === undefined) {
state.reading = false;
if (!state.ended)
onEofChunk(stream, state);
} else if (state.objectMode || chunk && chunk.length > 0) {
if (state.ended && !addToFront) {
var e = new Error('stream.push() after EOF');
stream.emit('error', e);
} else if (state.endEmitted && addToFront) {
var e = new Error('stream.unshift() after end event');
stream.emit('error', e);
} else {
if (state.decoder && !addToFront && !encoding)
chunk = state.decoder.write(chunk);
// update the buffer info.
state.length += state.objectMode ? 1 : chunk.length;
if (addToFront) {
state.buffer.unshift(chunk);
} else {
state.reading = false;
state.buffer.push(chunk);
}
if (state.needReadable)
emitReadable(stream);
maybeReadMore(stream, state);
}
} else if (!addToFront) {
state.reading = false;
}
return needMoreData(state);
}
// if it's past the high water mark, we can push in some more.
// Also, if we have no data yet, we can stand some
// more bytes. This is to work around cases where hwm=0,
// such as the repl. Also, if the push() triggered a
// readable event, and the user called read(largeNumber) such that
// needReadable was set, then we ought to push more, so that another
// 'readable' event will be triggered.
function needMoreData(state) {
return !state.ended &&
(state.needReadable ||
state.length < state.highWaterMark ||
state.length === 0);
}
// backwards compatibility.
Readable.prototype.setEncoding = function(enc) {
if (!StringDecoder)
StringDecoder = require('string_decoder/').StringDecoder;
this._readableState.decoder = new StringDecoder(enc);
this._readableState.encoding = enc;
};
// Don't raise the hwm > 128MB
var MAX_HWM = 0x800000;
function roundUpToNextPowerOf2(n) {
if (n >= MAX_HWM) {
n = MAX_HWM;
} else {
// Get the next highest power of 2
n--;
for (var p = 1; p < 32; p <<= 1) n |= n >> p;
n++;
}
return n;
}
function howMuchToRead(n, state) {
if (state.length === 0 && state.ended)
return 0;
if (state.objectMode)
return n === 0 ? 0 : 1;
if (n === null || isNaN(n)) {
// only flow one buffer at a time
if (state.flowing && state.buffer.length)
return state.buffer[0].length;
else
return state.length;
}
if (n <= 0)
return 0;
// If we're asking for more than the target buffer level,
// then raise the water mark. Bump up to the next highest
// power of 2, to prevent increasing it excessively in tiny
// amounts.
if (n > state.highWaterMark)
state.highWaterMark = roundUpToNextPowerOf2(n);
// don't have that much. return null, unless we've ended.
if (n > state.length) {
if (!state.ended) {
state.needReadable = true;
return 0;
} else
return state.length;
}
return n;
}
// you can override either this method, or the async _read(n) below.
Readable.prototype.read = function(n) {
var state = this._readableState;
state.calledRead = true;
var nOrig = n;
var ret;
if (typeof n !== 'number' || n > 0)
state.emittedReadable = false;
// if we're doing read(0) to trigger a readable event, but we
// already have a bunch of data in the buffer, then just trigger
// the 'readable' event and move on.
if (n === 0 &&
state.needReadable &&
(state.length >= state.highWaterMark || state.ended)) {
emitReadable(this);
return null;
}
n = howMuchToRead(n, state);
// if we've ended, and we're now clear, then finish it up.
if (n === 0 && state.ended) {
ret = null;
// In cases where the decoder did not receive enough data
// to produce a full chunk, then immediately received an
// EOF, state.buffer will contain [<Buffer >, <Buffer 00 ...>].
// howMuchToRead will see this and coerce the amount to
// read to zero (because it's looking at the length of the
// first <Buffer > in state.buffer), and we'll end up here.
//
// This can only happen via state.decoder -- no other venue
// exists for pushing a zero-length chunk into state.buffer
// and triggering this behavior. In this case, we return our
// remaining data and end the stream, if appropriate.
if (state.length > 0 && state.decoder) {
ret = fromList(n, state);
state.length -= ret.length;
}
if (state.length === 0)
endReadable(this);
return ret;
}
// All the actual chunk generation logic needs to be
// *below* the call to _read. The reason is that in certain
// synthetic stream cases, such as passthrough streams, _read
// may be a completely synchronous operation which may change
// the state of the read buffer, providing enough data when
// before there was *not* enough.
//
// So, the steps are:
// 1. Figure out what the state of things will be after we do
// a read from the buffer.
//
// 2. If that resulting state will trigger a _read, then call _read.
// Note that this may be asynchronous, or synchronous. Yes, it is
// deeply ugly to write APIs this way, but that still doesn't mean
// that the Readable class should behave improperly, as streams are
// designed to be sync/async agnostic.
// Take note if the _read call is sync or async (ie, if the read call
// has returned yet), so that we know whether or not it's safe to emit
// 'readable' etc.
//
// 3. Actually pull the requested chunks out of the buffer and return.
// if we need a readable event, then we need to do some reading.
var doRead = state.needReadable;
// if we currently have less than the highWaterMark, then also read some
if (state.length - n <= state.highWaterMark)
doRead = true;
// however, if we've ended, then there's no point, and if we're already
// reading, then it's unnecessary.
if (state.ended || state.reading)
doRead = false;
if (doRead) {
state.reading = true;
state.sync = true;
// if the length is currently zero, then we *need* a readable event.
if (state.length === 0)
state.needReadable = true;
// call internal read method
this._read(state.highWaterMark);
state.sync = false;
}
// If _read called its callback synchronously, then `reading`
// will be false, and we need to re-evaluate how much data we
// can return to the user.
if (doRead && !state.reading)
n = howMuchToRead(nOrig, state);
if (n > 0)
ret = fromList(n, state);
else
ret = null;
if (ret === null) {
state.needReadable = true;
n = 0;
}
state.length -= n;
// If we have nothing in the buffer, then we want to know
// as soon as we *do* get something into the buffer.
if (state.length === 0 && !state.ended)
state.needReadable = true;
// If we happened to read() exactly the remaining amount in the
// buffer, and the EOF has been seen at this point, then make sure
// that we emit 'end' on the very next tick.
if (state.ended && !state.endEmitted && state.length === 0)
endReadable(this);
return ret;
};
function chunkInvalid(state, chunk) {
var er = null;
if (!Buffer.isBuffer(chunk) &&
'string' !== typeof chunk &&
chunk !== null &&
chunk !== undefined &&
!state.objectMode) {
er = new TypeError('Invalid non-string/buffer chunk');
}
return er;
}
function onEofChunk(stream, state) {
if (state.decoder && !state.ended) {
var chunk = state.decoder.end();
if (chunk && chunk.length) {
state.buffer.push(chunk);
state.length += state.objectMode ? 1 : chunk.length;
}
}
state.ended = true;
// if we've ended and we have some data left, then emit
// 'readable' now to make sure it gets picked up.
if (state.length > 0)
emitReadable(stream);
else
endReadable(stream);
}
// Don't emit readable right away in sync mode, because this can trigger
// another read() call => stack overflow. This way, it might trigger
// a nextTick recursion warning, but that's not so bad.
function emitReadable(stream) {
var state = stream._readableState;
state.needReadable = false;
if (state.emittedReadable)
return;
state.emittedReadable = true;
if (state.sync)
process.nextTick(function() {
emitReadable_(stream);
});
else
emitReadable_(stream);
}
function emitReadable_(stream) {
stream.emit('readable');
}
// at this point, the user has presumably seen the 'readable' event,
// and called read() to consume some data. that may have triggered
// in turn another _read(n) call, in which case reading = true if
// it's in progress.
// However, if we're not ended, or reading, and the length < hwm,
// then go ahead and try to read some more preemptively.
function maybeReadMore(stream, state) {
if (!state.readingMore) {
state.readingMore = true;
process.nextTick(function() {
maybeReadMore_(stream, state);
});
}
}
function maybeReadMore_(stream, state) {
var len = state.length;
while (!state.reading && !state.flowing && !state.ended &&
state.length < state.highWaterMark) {
stream.read(0);
if (len === state.length)
// didn't get any data, stop spinning.
break;
else
len = state.length;
}
state.readingMore = false;
}
// abstract method. to be overridden in specific implementation classes.
// call cb(er, data) where data is <= n in length.
// for virtual (non-string, non-buffer) streams, "length" is somewhat
// arbitrary, and perhaps not very meaningful.
Readable.prototype._read = function(n) {
this.emit('error', new Error('not implemented'));
};
Readable.prototype.pipe = function(dest, pipeOpts) {
var src = this;
var state = this._readableState;
switch (state.pipesCount) {
case 0:
state.pipes = dest;
break;
case 1:
state.pipes = [state.pipes, dest];
break;
default:
state.pipes.push(dest);
break;
}
state.pipesCount += 1;
var doEnd = (!pipeOpts || pipeOpts.end !== false) &&
dest !== process.stdout &&
dest !== process.stderr;
var endFn = doEnd ? onend : cleanup;
if (state.endEmitted)
process.nextTick(endFn);
else
src.once('end', endFn);
dest.on('unpipe', onunpipe);
function onunpipe(readable) {
if (readable !== src) return;
cleanup();
}
function onend() {
dest.end();
}
// when the dest drains, it reduces the awaitDrain counter
// on the source. This would be more elegant with a .once()
// handler in flow(), but adding and removing repeatedly is
// too slow.
var ondrain = pipeOnDrain(src);
dest.on('drain', ondrain);
function cleanup() {
// cleanup event handlers once the pipe is broken
dest.removeListener('close', onclose);
dest.removeListener('finish', onfinish);
dest.removeListener('drain', ondrain);
dest.removeListener('error', onerror);
dest.removeListener('unpipe', onunpipe);
src.removeListener('end', onend);
src.removeListener('end', cleanup);
// if the reader is waiting for a drain event from this
// specific writer, then it would cause it to never start
// flowing again.
// So, if this is awaiting a drain, then we just call it now.
// If we don't know, then assume that we are waiting for one.
if (!dest._writableState || dest._writableState.needDrain)
ondrain();
}
// if the dest has an error, then stop piping into it.
// however, don't suppress the throwing behavior for this.
function onerror(er) {
unpipe();
dest.removeListener('error', onerror);
if (EE.listenerCount(dest, 'error') === 0)
dest.emit('error', er);
}
// This is a brutally ugly hack to make sure that our error handler
// is attached before any userland ones. NEVER DO THIS.
if (!dest._events || !dest._events.error)
dest.on('error', onerror);
else if (isArray(dest._events.error))
dest._events.error.unshift(onerror);
else
dest._events.error = [onerror, dest._events.error];
// Both close and finish should trigger unpipe, but only once.
function onclose() {
dest.removeListener('finish', onfinish);
unpipe();
}
dest.once('close', onclose);
function onfinish() {
dest.removeListener('close', onclose);
unpipe();
}
dest.once('finish', onfinish);
function unpipe() {
src.unpipe(dest);
}
// tell the dest that it's being piped to
dest.emit('pipe', src);
// start the flow if it hasn't been started already.
if (!state.flowing) {
// the handler that waits for readable events after all
// the data gets sucked out in flow.
// This would be easier to follow with a .once() handler
// in flow(), but that is too slow.
this.on('readable', pipeOnReadable);
state.flowing = true;
process.nextTick(function() {
flow(src);
});
}
return dest;
};
function pipeOnDrain(src) {
return function() {
var dest = this;
var state = src._readableState;
state.awaitDrain--;
if (state.awaitDrain === 0)
flow(src);
};
}
function flow(src) {
var state = src._readableState;
var chunk;
state.awaitDrain = 0;
function write(dest, i, list) {
var written = dest.write(chunk);
if (false === written) {
state.awaitDrain++;
}
}
while (state.pipesCount && null !== (chunk = src.read())) {
if (state.pipesCount === 1)
write(state.pipes, 0, null);
else
forEach(state.pipes, write);
src.emit('data', chunk);
// if anyone needs a drain, then we have to wait for that.
if (state.awaitDrain > 0)
return;
}
// if every destination was unpiped, either before entering this
// function, or in the while loop, then stop flowing.
//
// NB: This is a pretty rare edge case.
if (state.pipesCount === 0) {
state.flowing = false;
// if there were data event listeners added, then switch to old mode.
if (EE.listenerCount(src, 'data') > 0)
emitDataEvents(src);
return;
}
// at this point, no one needed a drain, so we just ran out of data
// on the next readable event, start it over again.
state.ranOut = true;
}
function pipeOnReadable() {
if (this._readableState.ranOut) {
this._readableState.ranOut = false;
flow(this);
}
}
Readable.prototype.unpipe = function(dest) {
var state = this._readableState;
// if we're not piping anywhere, then do nothing.
if (state.pipesCount === 0)
return this;
// just one destination. most common case.
if (state.pipesCount === 1) {
// passed in one, but it's not the right one.
if (dest && dest !== state.pipes)
return this;
if (!dest)
dest = state.pipes;
// got a match.
state.pipes = null;
state.pipesCount = 0;
this.removeListener('readable', pipeOnReadable);
state.flowing = false;
if (dest)
dest.emit('unpipe', this);
return this;
}
// slow case. multiple pipe destinations.
if (!dest) {
// remove all.
var dests = state.pipes;
var len = state.pipesCount;
state.pipes = null;
state.pipesCount = 0;
this.removeListener('readable', pipeOnReadable);
state.flowing = false;
for (var i = 0; i < len; i++)
dests[i].emit('unpipe', this);
return this;
}
// try to find the right one.
var i = indexOf(state.pipes, dest);
if (i === -1)
return this;
state.pipes.splice(i, 1);
state.pipesCount -= 1;
if (state.pipesCount === 1)
state.pipes = state.pipes[0];
dest.emit('unpipe', this);
return this;
};
// set up data events if they are asked for
// Ensure readable listeners eventually get something
Readable.prototype.on = function(ev, fn) {
var res = Stream.prototype.on.call(this, ev, fn);
if (ev === 'data' && !this._readableState.flowing)
emitDataEvents(this);
if (ev === 'readable' && this.readable) {
var state = this._readableState;
if (!state.readableListening) {
state.readableListening = true;
state.emittedReadable = false;
state.needReadable = true;
if (!state.reading) {
this.read(0);
} else if (state.length) {
emitReadable(this, state);
}
}
}
return res;
};
Readable.prototype.addListener = Readable.prototype.on;
// pause() and resume() are remnants of the legacy readable stream API
// If the user uses them, then switch into old mode.
Readable.prototype.resume = function() {
emitDataEvents(this);
this.read(0);
this.emit('resume');
};
Readable.prototype.pause = function() {
emitDataEvents(this, true);
this.emit('pause');
};
function emitDataEvents(stream, startPaused) {
var state = stream._readableState;
if (state.flowing) {
// https://github.com/isaacs/readable-stream/issues/16
throw new Error('Cannot switch to old mode now.');
}
var paused = startPaused || false;
var readable = false;
// convert to an old-style stream.
stream.readable = true;
stream.pipe = Stream.prototype.pipe;
stream.on = stream.addListener = Stream.prototype.on;
stream.on('readable', function() {
readable = true;
var c;
while (!paused && (null !== (c = stream.read())))
stream.emit('data', c);
if (c === null) {
readable = false;
stream._readableState.needReadable = true;
}
});
stream.pause = function() {
paused = true;
this.emit('pause');
};
stream.resume = function() {
paused = false;
if (readable)
process.nextTick(function() {
stream.emit('readable');
});
else
this.read(0);
this.emit('resume');
};
// now make it start, just in case it hadn't already.
stream.emit('readable');
}
// wrap an old-style stream as the async data source.
// This is *not* part of the readable stream interface.
// It is an ugly unfortunate mess of history.
Readable.prototype.wrap = function(stream) {
var state = this._readableState;
var paused = false;
var self = this;
stream.on('end', function() {
if (state.decoder && !state.ended) {
var chunk = state.decoder.end();
if (chunk && chunk.length)
self.push(chunk);
}
self.push(null);
});
stream.on('data', function(chunk) {
if (state.decoder)
chunk = state.decoder.write(chunk);
// don't skip over falsy values in objectMode
//if (state.objectMode && util.isNullOrUndefined(chunk))
if (state.objectMode && (chunk === null || chunk === undefined))
return;
else if (!state.objectMode && (!chunk || !chunk.length))
return;
var ret = self.push(chunk);
if (!ret) {
paused = true;
stream.pause();
}
});
// proxy all the other methods.
// important when wrapping filters and duplexes.
for (var i in stream) {
if (typeof stream[i] === 'function' &&
typeof this[i] === 'undefined') {
this[i] = function(method) { return function() {
return stream[method].apply(stream, arguments);
}}(i);
}
}
// proxy certain important events.
var events = ['error', 'close', 'destroy', 'pause', 'resume'];
forEach(events, function(ev) {
stream.on(ev, self.emit.bind(self, ev));
});
// when we try to consume some more bytes, simply unpause the
// underlying stream.
self._read = function(n) {
if (paused) {
paused = false;
stream.resume();
}
};
return self;
};
// exposed for testing purposes only.
Readable._fromList = fromList;
// Pluck off n bytes from an array of buffers.
// Length is the combined lengths of all the buffers in the list.
function fromList(n, state) {
var list = state.buffer;
var length = state.length;
var stringMode = !!state.decoder;
var objectMode = !!state.objectMode;
var ret;
// nothing in the list, definitely empty.
if (list.length === 0)
return null;
if (length === 0)
ret = null;
else if (objectMode)
ret = list.shift();
else if (!n || n >= length) {
// read it all, truncate the array.
if (stringMode)
ret = list.join('');
else
ret = Buffer.concat(list, length);
list.length = 0;
} else {
// read just some of it.
if (n < list[0].length) {
// just take a part of the first list item.
// slice is the same for buffers and strings.
var buf = list[0];
ret = buf.slice(0, n);
list[0] = buf.slice(n);
} else if (n === list[0].length) {
// first list is a perfect match
ret = list.shift();
} else {
// complex case.
// we have enough to cover it, but it spans past the first buffer.
if (stringMode)
ret = '';
else
ret = new Buffer(n);
var c = 0;
for (var i = 0, l = list.length; i < l && c < n; i++) {
var buf = list[0];
var cpy = Math.min(n - c, buf.length);
if (stringMode)
ret += buf.slice(0, cpy);
else
buf.copy(ret, c, 0, cpy);
if (cpy < buf.length)
list[0] = buf.slice(cpy);
else
list.shift();
c += cpy;
}
}
}
return ret;
}
function endReadable(stream) {
var state = stream._readableState;
// If we get here before consuming all the bytes, then that is a
// bug in node. Should never happen.
if (state.length > 0)
throw new Error('endReadable called on non-empty stream');
if (!state.endEmitted && state.calledRead) {
state.ended = true;
process.nextTick(function() {
// Check that we didn't get one last unshift.
if (!state.endEmitted && state.length === 0) {
state.endEmitted = true;
stream.readable = false;
stream.emit('end');
}
});
}
}
function forEach (xs, f) {
for (var i = 0, l = xs.length; i < l; i++) {
f(xs[i], i);
}
}
function indexOf (xs, x) {
for (var i = 0, l = xs.length; i < l; i++) {
if (xs[i] === x) return i;
}
return -1;
}

View File

@@ -0,0 +1,210 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
// a transform stream is a readable/writable stream where you do
// something with the data. Sometimes it's called a "filter",
// but that's not a great name for it, since that implies a thing where
// some bits pass through, and others are simply ignored. (That would
// be a valid example of a transform, of course.)
//
// While the output is causally related to the input, it's not a
// necessarily symmetric or synchronous transformation. For example,
// a zlib stream might take multiple plain-text writes(), and then
// emit a single compressed chunk some time in the future.
//
// Here's how this works:
//
// The Transform stream has all the aspects of the readable and writable
// stream classes. When you write(chunk), that calls _write(chunk,cb)
// internally, and returns false if there's a lot of pending writes
// buffered up. When you call read(), that calls _read(n) until
// there's enough pending readable data buffered up.
//
// In a transform stream, the written data is placed in a buffer. When
// _read(n) is called, it transforms the queued up data, calling the
// buffered _write cb's as it consumes chunks. If consuming a single
// written chunk would result in multiple output chunks, then the first
// outputted bit calls the readcb, and subsequent chunks just go into
// the read buffer, and will cause it to emit 'readable' if necessary.
//
// This way, back-pressure is actually determined by the reading side,
// since _read has to be called to start processing a new chunk. However,
// a pathological inflate type of transform can cause excessive buffering
// here. For example, imagine a stream where every byte of input is
// interpreted as an integer from 0-255, and then results in that many
// bytes of output. Writing the 4 bytes {ff,ff,ff,ff} would result in
// 1kb of data being output. In this case, you could write a very small
// amount of input, and end up with a very large amount of output. In
// such a pathological inflating mechanism, there'd be no way to tell
// the system to stop doing the transform. A single 4MB write could
// cause the system to run out of memory.
//
// However, even in such a pathological case, only a single written chunk
// would be consumed, and then the rest would wait (un-transformed) until
// the results of the previous transformed chunk were consumed.
module.exports = Transform;
var Duplex = require('./_stream_duplex');
/*<replacement>*/
var util = require('core-util-is');
util.inherits = require('inherits');
/*</replacement>*/
util.inherits(Transform, Duplex);
function TransformState(options, stream) {
this.afterTransform = function(er, data) {
return afterTransform(stream, er, data);
};
this.needTransform = false;
this.transforming = false;
this.writecb = null;
this.writechunk = null;
}
function afterTransform(stream, er, data) {
var ts = stream._transformState;
ts.transforming = false;
var cb = ts.writecb;
if (!cb)
return stream.emit('error', new Error('no writecb in Transform class'));
ts.writechunk = null;
ts.writecb = null;
if (data !== null && data !== undefined)
stream.push(data);
if (cb)
cb(er);
var rs = stream._readableState;
rs.reading = false;
if (rs.needReadable || rs.length < rs.highWaterMark) {
stream._read(rs.highWaterMark);
}
}
function Transform(options) {
if (!(this instanceof Transform))
return new Transform(options);
Duplex.call(this, options);
var ts = this._transformState = new TransformState(options, this);
// when the writable side finishes, then flush out anything remaining.
var stream = this;
// start out asking for a readable event once data is transformed.
this._readableState.needReadable = true;
// we have implemented the _read method, and done the other things
// that Readable wants before the first _read call, so unset the
// sync guard flag.
this._readableState.sync = false;
this.once('finish', function() {
if ('function' === typeof this._flush)
this._flush(function(er) {
done(stream, er);
});
else
done(stream);
});
}
Transform.prototype.push = function(chunk, encoding) {
this._transformState.needTransform = false;
return Duplex.prototype.push.call(this, chunk, encoding);
};
// This is the part where you do stuff!
// override this function in implementation classes.
// 'chunk' is an input chunk.
//
// Call `push(newChunk)` to pass along transformed output
// to the readable side. You may call 'push' zero or more times.
//
// Call `cb(err)` when you are done with this chunk. If you pass
// an error, then that'll put the hurt on the whole operation. If you
// never call cb(), then you'll never get another chunk.
Transform.prototype._transform = function(chunk, encoding, cb) {
throw new Error('not implemented');
};
Transform.prototype._write = function(chunk, encoding, cb) {
var ts = this._transformState;
ts.writecb = cb;
ts.writechunk = chunk;
ts.writeencoding = encoding;
if (!ts.transforming) {
var rs = this._readableState;
if (ts.needTransform ||
rs.needReadable ||
rs.length < rs.highWaterMark)
this._read(rs.highWaterMark);
}
};
// Doesn't matter what the args are here.
// _transform does all the work.
// That we got here means that the readable side wants more data.
Transform.prototype._read = function(n) {
var ts = this._transformState;
if (ts.writechunk !== null && ts.writecb && !ts.transforming) {
ts.transforming = true;
this._transform(ts.writechunk, ts.writeencoding, ts.afterTransform);
} else {
// mark that we need a transform, so that any data that comes in
// will get processed, now that we've asked for it.
ts.needTransform = true;
}
};
function done(stream, er) {
if (er)
return stream.emit('error', er);
// if there's nothing in the write buffer, then that means
// that nothing more will ever be provided
var ws = stream._writableState;
var rs = stream._readableState;
var ts = stream._transformState;
if (ws.length)
throw new Error('calling transform done when ws.length != 0');
if (ts.transforming)
throw new Error('calling transform done when still transforming');
return stream.push(null);
}

View File

@@ -0,0 +1,386 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
// A bit simpler than readable streams.
// Implement an async ._write(chunk, cb), and it'll handle all
// the drain event emission and buffering.
module.exports = Writable;
/*<replacement>*/
var Buffer = require('buffer').Buffer;
/*</replacement>*/
Writable.WritableState = WritableState;
/*<replacement>*/
var util = require('core-util-is');
util.inherits = require('inherits');
/*</replacement>*/
var Stream = require('stream');
util.inherits(Writable, Stream);
function WriteReq(chunk, encoding, cb) {
this.chunk = chunk;
this.encoding = encoding;
this.callback = cb;
}
function WritableState(options, stream) {
options = options || {};
// the point at which write() starts returning false
// Note: 0 is a valid value, means that we always return false if
// the entire buffer is not flushed immediately on write()
var hwm = options.highWaterMark;
this.highWaterMark = (hwm || hwm === 0) ? hwm : 16 * 1024;
// object stream flag to indicate whether or not this stream
// contains buffers or objects.
this.objectMode = !!options.objectMode;
// cast to ints.
this.highWaterMark = ~~this.highWaterMark;
this.needDrain = false;
// at the start of calling end()
this.ending = false;
// when end() has been called, and returned
this.ended = false;
// when 'finish' is emitted
this.finished = false;
// should we decode strings into buffers before passing to _write?
// this is here so that some node-core streams can optimize string
// handling at a lower level.
var noDecode = options.decodeStrings === false;
this.decodeStrings = !noDecode;
// Crypto is kind of old and crusty. Historically, its default string
// encoding is 'binary' so we have to make this configurable.
// Everything else in the universe uses 'utf8', though.
this.defaultEncoding = options.defaultEncoding || 'utf8';
// not an actual buffer we keep track of, but a measurement
// of how much we're waiting to get pushed to some underlying
// socket or file.
this.length = 0;
// a flag to see when we're in the middle of a write.
this.writing = false;
// a flag to be able to tell if the onwrite cb is called immediately,
// or on a later tick. We set this to true at first, becuase any
// actions that shouldn't happen until "later" should generally also
// not happen before the first write call.
this.sync = true;
// a flag to know if we're processing previously buffered items, which
// may call the _write() callback in the same tick, so that we don't
// end up in an overlapped onwrite situation.
this.bufferProcessing = false;
// the callback that's passed to _write(chunk,cb)
this.onwrite = function(er) {
onwrite(stream, er);
};
// the callback that the user supplies to write(chunk,encoding,cb)
this.writecb = null;
// the amount that is being written when _write is called.
this.writelen = 0;
this.buffer = [];
// True if the error was already emitted and should not be thrown again
this.errorEmitted = false;
}
function Writable(options) {
var Duplex = require('./_stream_duplex');
// Writable ctor is applied to Duplexes, though they're not
// instanceof Writable, they're instanceof Readable.
if (!(this instanceof Writable) && !(this instanceof Duplex))
return new Writable(options);
this._writableState = new WritableState(options, this);
// legacy.
this.writable = true;
Stream.call(this);
}
// Otherwise people can pipe Writable streams, which is just wrong.
Writable.prototype.pipe = function() {
this.emit('error', new Error('Cannot pipe. Not readable.'));
};
function writeAfterEnd(stream, state, cb) {
var er = new Error('write after end');
// TODO: defer error events consistently everywhere, not just the cb
stream.emit('error', er);
process.nextTick(function() {
cb(er);
});
}
// If we get something that is not a buffer, string, null, or undefined,
// and we're not in objectMode, then that's an error.
// Otherwise stream chunks are all considered to be of length=1, and the
// watermarks determine how many objects to keep in the buffer, rather than
// how many bytes or characters.
function validChunk(stream, state, chunk, cb) {
var valid = true;
if (!Buffer.isBuffer(chunk) &&
'string' !== typeof chunk &&
chunk !== null &&
chunk !== undefined &&
!state.objectMode) {
var er = new TypeError('Invalid non-string/buffer chunk');
stream.emit('error', er);
process.nextTick(function() {
cb(er);
});
valid = false;
}
return valid;
}
Writable.prototype.write = function(chunk, encoding, cb) {
var state = this._writableState;
var ret = false;
if (typeof encoding === 'function') {
cb = encoding;
encoding = null;
}
if (Buffer.isBuffer(chunk))
encoding = 'buffer';
else if (!encoding)
encoding = state.defaultEncoding;
if (typeof cb !== 'function')
cb = function() {};
if (state.ended)
writeAfterEnd(this, state, cb);
else if (validChunk(this, state, chunk, cb))
ret = writeOrBuffer(this, state, chunk, encoding, cb);
return ret;
};
function decodeChunk(state, chunk, encoding) {
if (!state.objectMode &&
state.decodeStrings !== false &&
typeof chunk === 'string') {
chunk = new Buffer(chunk, encoding);
}
return chunk;
}
// if we're already writing something, then just put this
// in the queue, and wait our turn. Otherwise, call _write
// If we return false, then we need a drain event, so set that flag.
function writeOrBuffer(stream, state, chunk, encoding, cb) {
chunk = decodeChunk(state, chunk, encoding);
if (Buffer.isBuffer(chunk))
encoding = 'buffer';
var len = state.objectMode ? 1 : chunk.length;
state.length += len;
var ret = state.length < state.highWaterMark;
// we must ensure that previous needDrain will not be reset to false.
if (!ret)
state.needDrain = true;
if (state.writing)
state.buffer.push(new WriteReq(chunk, encoding, cb));
else
doWrite(stream, state, len, chunk, encoding, cb);
return ret;
}
function doWrite(stream, state, len, chunk, encoding, cb) {
state.writelen = len;
state.writecb = cb;
state.writing = true;
state.sync = true;
stream._write(chunk, encoding, state.onwrite);
state.sync = false;
}
function onwriteError(stream, state, sync, er, cb) {
if (sync)
process.nextTick(function() {
cb(er);
});
else
cb(er);
stream._writableState.errorEmitted = true;
stream.emit('error', er);
}
function onwriteStateUpdate(state) {
state.writing = false;
state.writecb = null;
state.length -= state.writelen;
state.writelen = 0;
}
function onwrite(stream, er) {
var state = stream._writableState;
var sync = state.sync;
var cb = state.writecb;
onwriteStateUpdate(state);
if (er)
onwriteError(stream, state, sync, er, cb);
else {
// Check if we're actually ready to finish, but don't emit yet
var finished = needFinish(stream, state);
if (!finished && !state.bufferProcessing && state.buffer.length)
clearBuffer(stream, state);
if (sync) {
process.nextTick(function() {
afterWrite(stream, state, finished, cb);
});
} else {
afterWrite(stream, state, finished, cb);
}
}
}
function afterWrite(stream, state, finished, cb) {
if (!finished)
onwriteDrain(stream, state);
cb();
if (finished)
finishMaybe(stream, state);
}
// Must force callback to be called on nextTick, so that we don't
// emit 'drain' before the write() consumer gets the 'false' return
// value, and has a chance to attach a 'drain' listener.
function onwriteDrain(stream, state) {
if (state.length === 0 && state.needDrain) {
state.needDrain = false;
stream.emit('drain');
}
}
// if there's something in the buffer waiting, then process it
function clearBuffer(stream, state) {
state.bufferProcessing = true;
for (var c = 0; c < state.buffer.length; c++) {
var entry = state.buffer[c];
var chunk = entry.chunk;
var encoding = entry.encoding;
var cb = entry.callback;
var len = state.objectMode ? 1 : chunk.length;
doWrite(stream, state, len, chunk, encoding, cb);
// if we didn't call the onwrite immediately, then
// it means that we need to wait until it does.
// also, that means that the chunk and cb are currently
// being processed, so move the buffer counter past them.
if (state.writing) {
c++;
break;
}
}
state.bufferProcessing = false;
if (c < state.buffer.length)
state.buffer = state.buffer.slice(c);
else
state.buffer.length = 0;
}
Writable.prototype._write = function(chunk, encoding, cb) {
cb(new Error('not implemented'));
};
Writable.prototype.end = function(chunk, encoding, cb) {
var state = this._writableState;
if (typeof chunk === 'function') {
cb = chunk;
chunk = null;
encoding = null;
} else if (typeof encoding === 'function') {
cb = encoding;
encoding = null;
}
if (typeof chunk !== 'undefined' && chunk !== null)
this.write(chunk, encoding);
// ignore unnecessary end() calls.
if (!state.ending && !state.finished)
endWritable(this, state, cb);
};
function needFinish(stream, state) {
return (state.ending &&
state.length === 0 &&
!state.finished &&
!state.writing);
}
function finishMaybe(stream, state) {
var need = needFinish(stream, state);
if (need) {
state.finished = true;
stream.emit('finish');
}
return need;
}
function endWritable(stream, state, cb) {
state.ending = true;
finishMaybe(stream, state);
if (cb) {
if (state.finished)
process.nextTick(cb);
else
stream.once('finish', cb);
}
state.ended = true;
}

View File

@@ -0,0 +1,68 @@
{
"_args": [
[
"readable-stream@1.0.34",
"C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project"
]
],
"_from": "readable-stream@1.0.34",
"_id": "readable-stream@1.0.34",
"_inBundle": false,
"_integrity": "sha1-Elgg40vIQtLyqq+v5MKRbuMsFXw=",
"_location": "/react-scripts/htmlparser2/readable-stream",
"_phantomChildren": {},
"_requested": {
"type": "version",
"registry": true,
"raw": "readable-stream@1.0.34",
"name": "readable-stream",
"escapedName": "readable-stream",
"rawSpec": "1.0.34",
"saveSpec": null,
"fetchSpec": "1.0.34"
},
"_requiredBy": [
"/react-scripts/htmlparser2"
],
"_resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-1.0.34.tgz",
"_spec": "1.0.34",
"_where": "C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project",
"author": {
"name": "Isaac Z. Schlueter",
"email": "i@izs.me",
"url": "http://blog.izs.me/"
},
"browser": {
"util": false
},
"bugs": {
"url": "https://github.com/isaacs/readable-stream/issues"
},
"dependencies": {
"core-util-is": "~1.0.0",
"inherits": "~2.0.1",
"isarray": "0.0.1",
"string_decoder": "~0.10.x"
},
"description": "Streams2, a user-land copy of the stream library from Node.js v0.10.x",
"devDependencies": {
"tap": "~0.2.6"
},
"homepage": "https://github.com/isaacs/readable-stream#readme",
"keywords": [
"readable",
"stream",
"pipe"
],
"license": "MIT",
"main": "readable.js",
"name": "readable-stream",
"repository": {
"type": "git",
"url": "git://github.com/isaacs/readable-stream.git"
},
"scripts": {
"test": "tap test/simple/*.js"
},
"version": "1.0.34"
}

View File

@@ -0,0 +1 @@
module.exports = require("./lib/_stream_passthrough.js")

View File

@@ -0,0 +1,11 @@
var Stream = require('stream'); // hack to fix a circular dependency issue when used with browserify
exports = module.exports = require('./lib/_stream_readable.js');
exports.Stream = Stream;
exports.Readable = exports;
exports.Writable = require('./lib/_stream_writable.js');
exports.Duplex = require('./lib/_stream_duplex.js');
exports.Transform = require('./lib/_stream_transform.js');
exports.PassThrough = require('./lib/_stream_passthrough.js');
if (!process.browser && process.env.READABLE_STREAM === 'disable') {
module.exports = require('stream');
}

View File

@@ -0,0 +1 @@
module.exports = require("./lib/_stream_transform.js")

View File

@@ -0,0 +1 @@
module.exports = require("./lib/_stream_writable.js")

View File

@@ -0,0 +1,2 @@
build
test

View File

@@ -0,0 +1,20 @@
Copyright Joyent, Inc. and other Node contributors.
Permission is hereby granted, free of charge, to any person obtaining a
copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to permit
persons to whom the Software is furnished to do so, subject to the
following conditions:
The above copyright notice and this permission notice shall be included
in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
USE OR OTHER DEALINGS IN THE SOFTWARE.

View File

@@ -0,0 +1,7 @@
**string_decoder.js** (`require('string_decoder')`) from Node.js core
Copyright Joyent, Inc. and other Node contributors. See LICENCE file for details.
Version numbers match the versions found in Node core, e.g. 0.10.24 matches Node 0.10.24, likewise 0.11.10 matches Node 0.11.10. **Prefer the stable version over the unstable.**
The *build/* directory contains a build script that will scrape the source from the [joyent/node](https://github.com/joyent/node) repo given a specific Node version.

View File

@@ -0,0 +1,221 @@
// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
var Buffer = require('buffer').Buffer;
var isBufferEncoding = Buffer.isEncoding
|| function(encoding) {
switch (encoding && encoding.toLowerCase()) {
case 'hex': case 'utf8': case 'utf-8': case 'ascii': case 'binary': case 'base64': case 'ucs2': case 'ucs-2': case 'utf16le': case 'utf-16le': case 'raw': return true;
default: return false;
}
}
function assertEncoding(encoding) {
if (encoding && !isBufferEncoding(encoding)) {
throw new Error('Unknown encoding: ' + encoding);
}
}
// StringDecoder provides an interface for efficiently splitting a series of
// buffers into a series of JS strings without breaking apart multi-byte
// characters. CESU-8 is handled as part of the UTF-8 encoding.
//
// @TODO Handling all encodings inside a single object makes it very difficult
// to reason about this code, so it should be split up in the future.
// @TODO There should be a utf8-strict encoding that rejects invalid UTF-8 code
// points as used by CESU-8.
var StringDecoder = exports.StringDecoder = function(encoding) {
this.encoding = (encoding || 'utf8').toLowerCase().replace(/[-_]/, '');
assertEncoding(encoding);
switch (this.encoding) {
case 'utf8':
// CESU-8 represents each of Surrogate Pair by 3-bytes
this.surrogateSize = 3;
break;
case 'ucs2':
case 'utf16le':
// UTF-16 represents each of Surrogate Pair by 2-bytes
this.surrogateSize = 2;
this.detectIncompleteChar = utf16DetectIncompleteChar;
break;
case 'base64':
// Base-64 stores 3 bytes in 4 chars, and pads the remainder.
this.surrogateSize = 3;
this.detectIncompleteChar = base64DetectIncompleteChar;
break;
default:
this.write = passThroughWrite;
return;
}
// Enough space to store all bytes of a single character. UTF-8 needs 4
// bytes, but CESU-8 may require up to 6 (3 bytes per surrogate).
this.charBuffer = new Buffer(6);
// Number of bytes received for the current incomplete multi-byte character.
this.charReceived = 0;
// Number of bytes expected for the current incomplete multi-byte character.
this.charLength = 0;
};
// write decodes the given buffer and returns it as JS string that is
// guaranteed to not contain any partial multi-byte characters. Any partial
// character found at the end of the buffer is buffered up, and will be
// returned when calling write again with the remaining bytes.
//
// Note: Converting a Buffer containing an orphan surrogate to a String
// currently works, but converting a String to a Buffer (via `new Buffer`, or
// Buffer#write) will replace incomplete surrogates with the unicode
// replacement character. See https://codereview.chromium.org/121173009/ .
StringDecoder.prototype.write = function(buffer) {
var charStr = '';
// if our last write ended with an incomplete multibyte character
while (this.charLength) {
// determine how many remaining bytes this buffer has to offer for this char
var available = (buffer.length >= this.charLength - this.charReceived) ?
this.charLength - this.charReceived :
buffer.length;
// add the new bytes to the char buffer
buffer.copy(this.charBuffer, this.charReceived, 0, available);
this.charReceived += available;
if (this.charReceived < this.charLength) {
// still not enough chars in this buffer? wait for more ...
return '';
}
// remove bytes belonging to the current character from the buffer
buffer = buffer.slice(available, buffer.length);
// get the character that was split
charStr = this.charBuffer.slice(0, this.charLength).toString(this.encoding);
// CESU-8: lead surrogate (D800-DBFF) is also the incomplete character
var charCode = charStr.charCodeAt(charStr.length - 1);
if (charCode >= 0xD800 && charCode <= 0xDBFF) {
this.charLength += this.surrogateSize;
charStr = '';
continue;
}
this.charReceived = this.charLength = 0;
// if there are no more bytes in this buffer, just emit our char
if (buffer.length === 0) {
return charStr;
}
break;
}
// determine and set charLength / charReceived
this.detectIncompleteChar(buffer);
var end = buffer.length;
if (this.charLength) {
// buffer the incomplete character bytes we got
buffer.copy(this.charBuffer, 0, buffer.length - this.charReceived, end);
end -= this.charReceived;
}
charStr += buffer.toString(this.encoding, 0, end);
var end = charStr.length - 1;
var charCode = charStr.charCodeAt(end);
// CESU-8: lead surrogate (D800-DBFF) is also the incomplete character
if (charCode >= 0xD800 && charCode <= 0xDBFF) {
var size = this.surrogateSize;
this.charLength += size;
this.charReceived += size;
this.charBuffer.copy(this.charBuffer, size, 0, size);
buffer.copy(this.charBuffer, 0, 0, size);
return charStr.substring(0, end);
}
// or just emit the charStr
return charStr;
};
// detectIncompleteChar determines if there is an incomplete UTF-8 character at
// the end of the given buffer. If so, it sets this.charLength to the byte
// length that character, and sets this.charReceived to the number of bytes
// that are available for this character.
StringDecoder.prototype.detectIncompleteChar = function(buffer) {
// determine how many bytes we have to check at the end of this buffer
var i = (buffer.length >= 3) ? 3 : buffer.length;
// Figure out if one of the last i bytes of our buffer announces an
// incomplete char.
for (; i > 0; i--) {
var c = buffer[buffer.length - i];
// See http://en.wikipedia.org/wiki/UTF-8#Description
// 110XXXXX
if (i == 1 && c >> 5 == 0x06) {
this.charLength = 2;
break;
}
// 1110XXXX
if (i <= 2 && c >> 4 == 0x0E) {
this.charLength = 3;
break;
}
// 11110XXX
if (i <= 3 && c >> 3 == 0x1E) {
this.charLength = 4;
break;
}
}
this.charReceived = i;
};
StringDecoder.prototype.end = function(buffer) {
var res = '';
if (buffer && buffer.length)
res = this.write(buffer);
if (this.charReceived) {
var cr = this.charReceived;
var buf = this.charBuffer;
var enc = this.encoding;
res += buf.slice(0, cr).toString(enc);
}
return res;
};
function passThroughWrite(buffer) {
return buffer.toString(this.encoding);
}
function utf16DetectIncompleteChar(buffer) {
this.charReceived = buffer.length % 2;
this.charLength = this.charReceived ? 2 : 0;
}
function base64DetectIncompleteChar(buffer) {
this.charReceived = buffer.length % 3;
this.charLength = this.charReceived ? 3 : 0;
}

View File

@@ -0,0 +1,56 @@
{
"_args": [
[
"string_decoder@0.10.31",
"C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project"
]
],
"_from": "string_decoder@0.10.31",
"_id": "string_decoder@0.10.31",
"_inBundle": false,
"_integrity": "sha1-YuIDvEF2bGwoyfyEMB2rHFMQ+pQ=",
"_location": "/react-scripts/htmlparser2/string_decoder",
"_phantomChildren": {},
"_requested": {
"type": "version",
"registry": true,
"raw": "string_decoder@0.10.31",
"name": "string_decoder",
"escapedName": "string_decoder",
"rawSpec": "0.10.31",
"saveSpec": null,
"fetchSpec": "0.10.31"
},
"_requiredBy": [
"/react-scripts/htmlparser2/readable-stream"
],
"_resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-0.10.31.tgz",
"_spec": "0.10.31",
"_where": "C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project",
"bugs": {
"url": "https://github.com/rvagg/string_decoder/issues"
},
"dependencies": {},
"description": "The string_decoder module from Node core",
"devDependencies": {
"tap": "~0.4.8"
},
"homepage": "https://github.com/rvagg/string_decoder",
"keywords": [
"string",
"decoder",
"browser",
"browserify"
],
"license": "MIT",
"main": "index.js",
"name": "string_decoder",
"repository": {
"type": "git",
"url": "git://github.com/rvagg/string_decoder.git"
},
"scripts": {
"test": "tap test/simple/*.js"
},
"version": "0.10.31"
}

View File

@@ -0,0 +1,87 @@
{
"_args": [
[
"htmlparser2@3.3.0",
"C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project"
]
],
"_from": "htmlparser2@3.3.0",
"_id": "htmlparser2@3.3.0",
"_inBundle": false,
"_integrity": "sha1-zHDQWln2VC5D8OaFyYLhTJJKnv4=",
"_location": "/react-scripts/htmlparser2",
"_phantomChildren": {
"core-util-is": "1.0.2",
"domelementtype": "1.3.0",
"inherits": "2.0.3"
},
"_requested": {
"type": "version",
"registry": true,
"raw": "htmlparser2@3.3.0",
"name": "htmlparser2",
"escapedName": "htmlparser2",
"rawSpec": "3.3.0",
"saveSpec": null,
"fetchSpec": "3.3.0"
},
"_requiredBy": [
"/react-scripts/renderkid"
],
"_resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-3.3.0.tgz",
"_spec": "3.3.0",
"_where": "C:\\Users\\deranjer\\go\\src\\github.com\\deranjer\\goTorrent\\torrent-project",
"author": {
"name": "Felix Boehm",
"email": "me@feedic.com"
},
"bugs": {
"url": "http://github.com/fb55/htmlparser2/issues"
},
"contributors": [
{
"name": "Chris Winberry",
"email": "chris@winberry.net"
}
],
"dependencies": {
"domelementtype": "1",
"domhandler": "2.1",
"domutils": "1.1",
"readable-stream": "1.0"
},
"description": "Fast & forgiving HTML/XML/RSS parser",
"devDependencies": {
"mocha": "1"
},
"directories": {
"lib": "lib/"
},
"homepage": "https://github.com/fb55/htmlparser2#readme",
"keywords": [
"html",
"parser",
"streams",
"xml",
"dom",
"rss",
"feed",
"atom"
],
"licenses": [
{
"type": "MIT",
"url": "http://github.com/fb55/htmlparser2/raw/master/LICENSE"
}
],
"main": "lib/index.js",
"name": "htmlparser2",
"repository": {
"type": "git",
"url": "git://github.com/fb55/htmlparser2.git"
},
"scripts": {
"test": "mocha -R spec"
},
"version": "3.3.0"
}

View File

@@ -0,0 +1,9 @@
var helper = require("./test-helper.js");
helper.mochaTest("Events", __dirname, function(test, cb){
helper.writeToParser(
helper.getEventCollector(cb),
test.options.parser,
test.html
);
});

View File

@@ -0,0 +1,23 @@
var helper = require("./test-helper.js"),
Stream = require("..").WritableStream,
fs = require("fs"),
path = require("path");
helper.mochaTest("Stream", __dirname, function(test, cb){
var filePath = path.join(__dirname, "Documents", test.file);
fs.createReadStream(filePath).pipe(
new Stream(
helper.getEventCollector(function(err, events){
cb(err, events);
var handler = helper.getEventCollector(cb),
stream = new Stream(handler, test.options);
fs.readFile(filePath, function(err, data){
if(err) throw err;
else stream.end(data);
});
}
), test.options)
).on("error", cb);
});

View File

@@ -0,0 +1,19 @@
//Runs tests for feeds
var helper = require("./test-helper.js"),
FeedHandler = require("../lib/FeedHandler.js"),
fs = require("fs"),
path = require("path");
helper.mochaTest("Feeds", __dirname, function(test, cb){
fs.readFile(
path.join(__dirname, "Documents", test.file),
function(err, file){
helper.writeToParser(
new FeedHandler(cb),
{ xmlMode: true },
file.toString()
);
}
);
});

View File

@@ -0,0 +1,25 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- http://en.wikipedia.org/wiki/Atom_%28standard%29 -->
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<subtitle>A subtitle.</subtitle>
<link href="http://example.org/feed/" rel="self" />
<link href="http://example.org/" />
<id>urn:uuid:60a76c80-d399-11d9-b91C-0003939e0af6</id>
<updated>2003-12-13T18:30:02Z</updated>
<author>
<name>John Doe</name>
<email>johndoe@example.com</email>
</author>
<entry>
<title>Atom-Powered Robots Run Amok</title>
<link href="http://example.org/2003/12/13/atom03" />
<link rel="alternate" type="text/html" href="http://example.org/2003/12/13/atom03.html"/>
<link rel="edit" href="http://example.org/2003/12/13/atom03/edit"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>

View File

@@ -0,0 +1,16 @@
<!doctype html>
<html>
<head>
<title>Attributes test</title>
</head>
<body>
<!-- Normal attributes -->
<button id="test0" class="value0" title="value1">class="value0" title="value1"</button>
<!-- Attributes with no quotes or value -->
<button id="test1" class=value2 disabled>class=value2 disabled</button>
<!-- Attributes with no space between them. No valid, but accepted by the browser -->
<button id="test2" class="value4"title="value5">class="value4"title="value5"</button>
</body>
</html>

View File

@@ -0,0 +1 @@
<!DOCTYPE html><html><title>The Title</title><body>Hello world</body></html>

View File

@@ -0,0 +1,63 @@
<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/" xmlns:ev="http://purl.org/rss/1.0/modules/event/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:admin="http://webns.net/mvcb/">
<channel rdf:about="http://sfbay.craigslist.org/ccc/">
<title>craigslist | all community in SF bay area</title>
<link>http://sfbay.craigslist.org/ccc/</link>
<description/>
<dc:language>en-us</dc:language>
<dc:rights>Copyright 2011 craigslist, inc.</dc:rights>
<dc:publisher>webmaster@craigslist.org</dc:publisher>
<dc:creator>webmaster@craigslist.org</dc:creator>
<dc:source>http://sfbay.craigslist.org/ccc//</dc:source>
<dc:title>craigslist | all community in SF bay area</dc:title>
<dc:type>Collection</dc:type>
<syn:updateBase>2011-11-04T09:39:10-07:00</syn:updateBase>
<syn:updateFrequency>4</syn:updateFrequency>
<syn:updatePeriod>hourly</syn:updatePeriod>
<items>
<rdf:Seq>
<rdf:li rdf:resource="http://sfbay.craigslist.org/sby/muc/2681301534.html"/>
</rdf:Seq>
</items>
</channel>
<item rdf:about="http://sfbay.craigslist.org/sby/muc/2681301534.html">
<title><![CDATA[ Music Equipment Repair and Consignment ]]></title>
<link>
http://sfbay.craigslist.org/sby/muc/2681301534.html
</link>
<description><![CDATA[
San Jose Rock Shop offers musical instrument repair and consignment! (408) 215-2065<br> <br> We are pleased to announce our NEW LOCATION: 1199 N 5th st. San Jose, ca 95112. Please call ahead, by appointment only.<br> <br> Recently featured by Metro Newspaper in their 2011 Best of the Silicon Valley edition see it online here:<br> <a href="http://www.metroactive.com/best-of-silicon-valley/2011/music-nightlife/editor-picks.html" rel="nofollow">http://www.metroactive.com/best-of-silicon-valley/2011/music-nightlife/editor-picks.html</a><br> <br> Guitar Set up (acoustic and electronic) $40!<!-- END CLTAGS -->
]]></description>
<dc:date>2011-11-04T09:35:17-07:00</dc:date>
<dc:language>en-us</dc:language>
<dc:rights>Copyright 2011 craigslist, inc.</dc:rights>
<dc:source>
http://sfbay.craigslist.org/sby/muc/2681301534.html
</dc:source>
<dc:title><![CDATA[ Music Equipment Repair and Consignment ]]></dc:title>
<dc:type>text</dc:type>
<dcterms:issued>2011-11-04T09:35:17-07:00</dcterms:issued>
</item>
<item rdf:about="http://sfbay.craigslist.org/eby/rid/2685010755.html">
<title><![CDATA[
Ride Offered - Oakland/BART to LA/SFV - TODAY 3PM 11/04 (oakland north / temescal)
]]></title>
<link>
http://sfbay.craigslist.org/eby/rid/2685010755.html
</link>
<description><![CDATA[
Im offering a lift for up to two people from Oakland (or near any BART station in the East Bay/580/880 Corridor, or San Jose/Morgan Hill, Gilroy) to the San Fernando Valley / Los Angeles area. Specifically, Im leaving from Oakland between 2:30 and 3:00pm (this is flexible, but if I leave too late my girlfriend will kill me), and heading to Woodland Hills via the 580, I-5, 405, and 101.<!-- END CLTAGS -->
]]></description>
<dc:date>2011-11-04T09:34:54-07:00</dc:date>
<dc:language>en-us</dc:language>
<dc:rights>Copyright 2011 craigslist, inc.</dc:rights>
<dc:source>
http://sfbay.craigslist.org/eby/rid/2685010755.html
</dc:source>
<dc:title><![CDATA[
Ride Offered - Oakland/BART to LA/SFV - TODAY 3PM 11/04 (oakland north / temescal)
]]></dc:title>
<dc:type>text</dc:type>
<dcterms:issued>2011-11-04T09:34:54-07:00</dcterms:issued>
</item>
</rdf:RDF>

View File

@@ -0,0 +1,48 @@
<?xml version="1.0"?>
<!-- http://cyber.law.harvard.edu/rss/examples/rss2sample.xml -->
<rss version="2.0">
<channel>
<title>Liftoff News</title>
<link>http://liftoff.msfc.nasa.gov/</link>
<description>Liftoff to Space Exploration.</description>
<language>en-us</language>
<pubDate>Tue, 10 Jun 2003 04:00:00 GMT</pubDate>
<lastBuildDate>Tue, 10 Jun 2003 09:41:01 GMT</lastBuildDate>
<docs>http://blogs.law.harvard.edu/tech/rss</docs>
<generator>Weblog Editor 2.0</generator>
<managingEditor>editor@example.com</managingEditor>
<webMaster>webmaster@example.com</webMaster>
<item>
<title>Star City</title>
<link>http://liftoff.msfc.nasa.gov/news/2003/news-starcity.asp</link>
<description>How do Americans get ready to work with Russians aboard the International Space Station? They take a crash course in culture, language and protocol at Russia's &lt;a href="http://howe.iki.rssi.ru/GCTC/gctc_e.htm"&gt;Star City&lt;/a&gt;.</description>
<pubDate>Tue, 03 Jun 2003 09:39:21 GMT</pubDate>
<guid>http://liftoff.msfc.nasa.gov/2003/06/03.html#item573</guid>
</item>
<item>
<description>Sky watchers in Europe, Asia, and parts of Alaska and Canada will experience a &lt;a href="http://science.nasa.gov/headlines/y2003/30may_solareclipse.htm"&gt;partial eclipse of the Sun&lt;/a&gt; on Saturday, May 31st.</description>
<pubDate>Fri, 30 May 2003 11:06:42 GMT</pubDate>
<guid>http://liftoff.msfc.nasa.gov/2003/05/30.html#item572</guid>
</item>
<item>
<title>The Engine That Does More</title>
<link>http://liftoff.msfc.nasa.gov/news/2003/news-VASIMR.asp</link>
<description>Before man travels to Mars, NASA hopes to design new engines that will let us fly through the Solar System more quickly. The proposed VASIMR engine would do that.</description>
<pubDate>Tue, 27 May 2003 08:37:32 GMT</pubDate>
<guid>http://liftoff.msfc.nasa.gov/2003/05/27.html#item571</guid>
</item>
<item>
<title>Astronauts' Dirty Laundry</title>
<link>http://liftoff.msfc.nasa.gov/news/2003/news-laundry.asp</link>
<description>Compared to earlier spacecraft, the International Space Station has many luxuries, but laundry facilities are not one of them. Instead, astronauts have other options.</description>
<pubDate>Tue, 20 May 2003 08:56:02 GMT</pubDate>
<guid>http://liftoff.msfc.nasa.gov/2003/05/20.html#item570</guid>
</item>
</channel>
</rss>

View File

@@ -0,0 +1,44 @@
{
"name": "simple",
"options": {
"handler": {},
"parser": {}
},
"html": "<h1 class=test>adsf</h1>",
"expected": [
{
"event": "opentagname",
"data": [
"h1"
]
},
{
"event": "attribute",
"data": [
"class",
"test"
]
},
{
"event": "opentag",
"data": [
"h1",
{
"class": "test"
}
]
},
{
"event": "text",
"data": [
"adsf"
]
},
{
"event": "closetag",
"data": [
"h1"
]
}
]
}

View File

@@ -0,0 +1,63 @@
{
"name": "Template script tags",
"options": {
"handler": {},
"parser": {}
},
"html": "<p><script type=\"text/template\"><h1>Heading1</h1></script></p>",
"expected": [
{
"event": "opentagname",
"data": [
"p"
]
},
{
"event": "opentag",
"data": [
"p",
{}
]
},
{
"event": "opentagname",
"data": [
"script"
]
},
{
"event": "attribute",
"data": [
"type",
"text/template"
]
},
{
"event": "opentag",
"data": [
"script",
{
"type": "text/template"
}
]
},
{
"event": "text",
"data": [
"<h1>Heading1</h1>"
]
},
{
"event": "closetag",
"data": [
"script"
]
},
{
"event": "closetag",
"data": [
"p"
]
}
]
}

View File

@@ -0,0 +1,46 @@
{
"name": "Lowercase tags",
"options": {
"handler": {},
"parser": {
"lowerCaseTags": true
}
},
"html": "<H1 class=test>adsf</H1>",
"expected": [
{
"event": "opentagname",
"data": [
"h1"
]
},
{
"event": "attribute",
"data": [
"class",
"test"
]
},
{
"event": "opentag",
"data": [
"h1",
{
"class": "test"
}
]
},
{
"event": "text",
"data": [
"adsf"
]
},
{
"event": "closetag",
"data": [
"h1"
]
}
]
}

View File

@@ -0,0 +1,43 @@
{
"name": "CDATA",
"options": {
"handler": {},
"parser": {"xmlMode": true}
},
"html": "<tag><![CDATA[ asdf ><asdf></adsf><> fo]]></tag>",
"expected": [
{
"event": "opentagname",
"data": [
"tag"
]
},
{
"event": "opentag",
"data": [
"tag",
{}
]
},
{
"event": "cdatastart",
"data": []
},
{
"event": "text",
"data": [
" asdf ><asdf></adsf><> fo"
]
},
{
"event": "cdataend",
"data": []
},
{
"event": "closetag",
"data": [
"tag"
]
}
]
}

View File

@@ -0,0 +1,35 @@
{
"name": "CDATA (inside special)",
"options": {
"handler": {},
"parser": {}
},
"html": "<script>/*<![CDATA[*/ asdf ><asdf></adsf><> fo/*]]>*/</script>",
"expected": [
{
"event": "opentagname",
"data": [
"script"
]
},
{
"event": "opentag",
"data": [
"script",
{}
]
},
{
"event": "text",
"data": [
"/*<![CDATA[*/ asdf ><asdf></adsf><> fo/*]]>*/"
]
},
{
"event": "closetag",
"data": [
"script"
]
}
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "leading lt",
"options": {
"handler": {},
"parser": {}
},
"html": ">a>",
"expected": [
{
"event": "text",
"data": [
">a>"
]
}
]
}

View File

@@ -0,0 +1,67 @@
{
"name": "Self-closing tags",
"options": {
"handler": {
},
"parser": {
}
},
"html": "<a href=http://test.com/>Foo</a><hr />",
"expected": [
{
"event": "opentagname",
"data": [
"a"
]
},
{
"event": "attribute",
"data": [
"href",
"http://test.com/"
]
},
{
"event": "opentag",
"data": [
"a",
{
"href": "http://test.com/"
}
]
},
{
"event": "text",
"data": [
"Foo"
]
},
{
"event": "closetag",
"data": [
"a"
]
},
{
"event": "opentagname",
"data": [
"hr"
]
},
{
"event": "opentag",
"data": [
"hr",
{}
]
},
{
"event": "closetag",
"data": [
"hr"
]
}
]
}

View File

@@ -0,0 +1,59 @@
{
"name": "Implicit close tags",
"options": {},
"html": "<ol><li class=test><div><table style=width:100%><tr><td colspan=2><h3>Heading</h3><tr><td><div>Div</div><td><div>Div2</div></table></div><li><div><h3>Heading 2</h3></div></li></ol>",
"expected": [
{ "event": "opentagname", "data": [ "ol" ] },
{ "event": "opentag", "data": [ "ol", {} ] },
{ "event": "opentagname", "data": [ "li" ] },
{ "event": "attribute", "data": [ "class", "test" ] },
{ "event": "opentag", "data": [ "li", { "class": "test" } ] },
{ "event": "opentagname", "data": [ "div" ] },
{ "event": "opentag", "data": [ "div", {} ] },
{ "event": "opentagname", "data": [ "table" ] },
{ "event": "attribute", "data": [ "style", "width:100%" ] },
{ "event": "opentag", "data": [ "table", { "style": "width:100%" } ] },
{ "event": "opentagname", "data": [ "tr" ] },
{ "event": "opentag", "data": [ "tr", {} ] },
{ "event": "opentagname", "data": [ "td" ] },
{ "event": "attribute", "data": [ "colspan", "2" ] },
{ "event": "opentag", "data": [ "td", { "colspan": "2" } ] },
{ "event": "opentagname", "data": [ "h3" ] },
{ "event": "opentag", "data": [ "h3", {} ] },
{ "event": "text", "data": [ "Heading" ] },
{ "event": "closetag", "data": [ "h3" ] },
{ "event": "closetag", "data": [ "td" ] },
{ "event": "closetag", "data": [ "tr" ] },
{ "event": "opentagname", "data": [ "tr" ] },
{ "event": "opentag", "data": [ "tr", {} ] },
{ "event": "opentagname", "data": [ "td" ] },
{ "event": "opentag", "data": [ "td", {} ] },
{ "event": "opentagname", "data": [ "div" ] },
{ "event": "opentag", "data": [ "div", {} ] },
{ "event": "text", "data": [ "Div" ] },
{ "event": "closetag", "data": [ "div" ] },
{ "event": "closetag", "data": [ "td" ] },
{ "event": "opentagname", "data": [ "td" ] },
{ "event": "opentag", "data": [ "td", {} ] },
{ "event": "opentagname", "data": [ "div" ] },
{ "event": "opentag", "data": [ "div", {} ] },
{ "event": "text", "data": [ "Div2" ] },
{ "event": "closetag", "data": [ "div" ] },
{ "event": "closetag", "data": [ "td" ] },
{ "event": "closetag", "data": [ "tr" ] },
{ "event": "closetag", "data": [ "table" ] },
{ "event": "closetag", "data": [ "div" ] },
{ "event": "closetag", "data": [ "li" ] },
{ "event": "opentagname", "data": [ "li" ] },
{ "event": "opentag", "data": [ "li", {} ] },
{ "event": "opentagname", "data": [ "div" ] },
{ "event": "opentag", "data": [ "div", {} ] },
{ "event": "opentagname", "data": [ "h3" ] },
{ "event": "opentag", "data": [ "h3", {} ] },
{ "event": "text", "data": [ "Heading 2" ] },
{ "event": "closetag", "data": [ "h3" ] },
{ "event": "closetag", "data": [ "div" ] },
{ "event": "closetag", "data": [ "li" ] },
{ "event": "closetag", "data": [ "ol" ] }
]
}

View File

@@ -0,0 +1,68 @@
{
"name": "attributes (no white space, no value, no quotes)",
"options": {
"handler": {},
"parser": {}
},
"html": "<button class=\"test0\"title=\"test1\" disabled value=test2>adsf</button>",
"expected": [
{
"event": "opentagname",
"data": [
"button"
]
},
{
"event": "attribute",
"data": [
"class",
"test0"
]
},
{
"event": "attribute",
"data": [
"title",
"test1"
]
},
{
"event": "attribute",
"data": [
"disabled",
""
]
},
{
"event": "attribute",
"data": [
"value",
"test2"
]
},
{
"event": "opentag",
"data": [
"button",
{
"class": "test0",
"title": "test1",
"disabled": "",
"value": "test2"
}
]
},
{
"event": "text",
"data": [
"adsf"
]
},
{
"event": "closetag",
"data": [
"button"
]
}
]
}

View File

@@ -0,0 +1,52 @@
{
"name": "crazy attribute",
"options": {
"handler": {},
"parser": {}
},
"html": "<p <='' FAIL>stuff</p>",
"expected": [
{
"event": "opentagname",
"data": [
"p"
]
},
{
"event": "attribute",
"data": [
"<",
""
]
},
{
"event": "attribute",
"data": [
"fail",
""
]
},
{
"event": "opentag",
"data": [
"p",
{
"<": "",
"fail": ""
}
]
},
{
"event": "text",
"data": [
"stuff"
]
},
{
"event": "closetag",
"data": [
"p"
]
}
]
}

View File

@@ -0,0 +1,54 @@
{
"name": "Scripts creating other scripts",
"options": {
"handler": {},
"parser": {}
},
"html": "<p><script>var str = '<script></'+'script>';</script></p>",
"expected": [
{
"event": "opentagname",
"data": [
"p"
]
},
{
"event": "opentag",
"data": [
"p",
{}
]
},
{
"event": "opentagname",
"data": [
"script"
]
},
{
"event": "opentag",
"data": [
"script",
{}
]
},
{
"event": "text",
"data": [
"var str = '<script></'+'script>';"
]
},
{
"event": "closetag",
"data": [
"script"
]
},
{
"event": "closetag",
"data": [
"p"
]
}
]
}

View File

@@ -0,0 +1,20 @@
{
"name": "Long comment ending",
"options": {
"handler": {},
"parser": {}
},
"html": "<meta id='before'><!-- text ---><meta id='after'>",
"expected": [
{ "event": "opentagname", "data": [ "meta" ] },
{ "event": "attribute", "data": [ "id", "before" ] },
{ "event": "opentag", "data": [ "meta", {"id": "before"} ] },
{ "event": "closetag", "data": [ "meta" ] },
{ "event": "comment", "data": [ " text -" ] },
{ "event": "commentend", "data": [] },
{ "event": "opentagname", "data": [ "meta" ] },
{ "event": "attribute", "data": [ "id", "after" ] },
{ "event": "opentag", "data": [ "meta", {"id": "after"} ] },
{ "event": "closetag", "data": [ "meta" ] }
]
}

View File

@@ -0,0 +1,22 @@
{
"name": "Long CDATA ending",
"options": {
"handler": {},
"parser": {"xmlMode": true}
},
"html": "<before /><tag><![CDATA[ text ]]]></tag><after />",
"expected": [
{ "event": "opentagname", "data": [ "before" ] },
{ "event": "opentag", "data": [ "before", {} ] },
{ "event": "closetag", "data": [ "before" ] },
{ "event": "opentagname", "data": [ "tag" ] },
{ "event": "opentag", "data": [ "tag", {} ] },
{ "event": "cdatastart", "data": [] },
{ "event": "text", "data": [ " text ]" ] },
{ "event": "cdataend", "data": [] },
{ "event": "closetag", "data": [ "tag" ] },
{ "event": "opentagname", "data": [ "after" ] },
{ "event": "opentag", "data": [ "after", {} ] },
{ "event": "closetag", "data": [ "after" ] }
]
}

View File

@@ -0,0 +1,24 @@
{
"name": "Implicit open p and br tags",
"options": {
"handler": {},
"parser": {}
},
"html": "<div>Hallo</p>World</br></div></p>",
"expected": [
{ "event": "opentagname", "data": [ "div" ] },
{ "event": "opentag", "data": [ "div", {} ] },
{ "event": "text", "data": [ "Hallo" ] },
{ "event": "opentagname", "data": [ "p" ] },
{ "event": "opentag", "data": [ "p", {} ] },
{ "event": "closetag", "data": [ "p" ] },
{ "event": "text", "data": [ "World" ] },
{ "event": "opentagname", "data": [ "br" ] },
{ "event": "opentag", "data": [ "br", {} ] },
{ "event": "closetag", "data": [ "br" ] },
{ "event": "closetag", "data": [ "div" ] },
{ "event": "opentagname", "data": [ "p" ] },
{ "event": "opentag", "data": [ "p", {} ] },
{ "event": "closetag", "data": [ "p" ] }
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "lt followed by whitespace",
"options": {
"handler": {},
"parser": {}
},
"html": "a < b",
"expected": [
{
"event": "text",
"data": [
"a < b"
]
}
]
}

View File

@@ -0,0 +1,45 @@
{
"name": "double attribute",
"options": {
"handler": {},
"parser": {}
},
"html": "<h1 class=test class=boo></h1>",
"expected": [
{
"event": "opentagname",
"data": [
"h1"
]
},
{
"event": "attribute",
"data": [
"class",
"test"
]
},
{
"event": "attribute",
"data": [
"class",
"boo"
]
},
{
"event": "opentag",
"data": [
"h1",
{
"class": "test"
}
]
},
{
"event": "closetag",
"data": [
"h1"
]
}
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "numeric entities",
"options": {
"handler": {},
"parser": {"decodeEntities": true}
},
"html": "&#x61;&#x62&#99;&#100",
"expected": [
{
"event": "text",
"data": [
"abcd"
]
}
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "legacy entities",
"options": {
"handler": {},
"parser": {"decodeEntities": true}
},
"html": "&AMPel&iacutees&lter",
"expected": [
{
"event": "text",
"data": [
"&el\u00EDes<er"
]
}
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "named entities",
"options": {
"handler": {},
"parser": {"decodeEntities": true}
},
"html": "&amp;el&lt;er&CounterClockwiseContourIntegral;foo",
"expected": [
{
"event": "text",
"data": [
"&el<er\u2233foo"
]
}
]
}

View File

@@ -0,0 +1,16 @@
{
"name": "xml entities",
"options": {
"handler": {},
"parser": {"decodeEntities": true, "xmlMode": true}
},
"html": "&amp;&gt;&amp&lt;&uuml;&#x61;&#x62&#99;&#100",
"expected": [
{
"event": "text",
"data": [
"&>&amp<&uuml;a&#x62c&#100"
]
}
]
}

View File

@@ -0,0 +1,38 @@
{
"name": "entity in attribute",
"options": {
"handler": {},
"parser": {"decodeEntities": true}
},
"html": "<a href='http://example.com/p&#x61;ge?param=value&param2=&lt;val'>",
"expected": [
{
"event": "opentagname",
"data": [
"a"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.com/page?param=value&param2=<val"
]
},
{
"event": "opentag",
"data": [
"a",
{
"href": "http://example.com/page?param=value&param2=<val"
}
]
},
{
"event": "closetag",
"data": [
"a"
]
}
]
}

View File

@@ -0,0 +1,41 @@
{
"name": "double brackets",
"options": {
"handler": {},
"parser": {}
},
"html": "<<princess-purpose>>testing</princess-purpose>",
"expected": [
{
"event": "text",
"data": [
"<"
]
},
{
"event": "opentagname",
"data": [
"princess-purpose"
]
},
{
"event": "opentag",
"data": [
"princess-purpose",
{}
]
},
{
"event": "text",
"data": [
">testing"
]
},
{
"event": "closetag",
"data": [
"princess-purpose"
]
}
]
}

View File

@@ -0,0 +1,34 @@
exports.name = "RSS (2.0)";
exports.file = "/RSS_Example.xml";
exports.expected = {
type: "rss",
id: "",
title: "Liftoff News",
link: "http://liftoff.msfc.nasa.gov/",
description: "Liftoff to Space Exploration.",
updated: new Date("Tue, 10 Jun 2003 09:41:01 GMT"),
author: "editor@example.com",
items: [{
id: "http://liftoff.msfc.nasa.gov/2003/06/03.html#item573",
title: "Star City",
link: "http://liftoff.msfc.nasa.gov/news/2003/news-starcity.asp",
description: "How do Americans get ready to work with Russians aboard the International Space Station? They take a crash course in culture, language and protocol at Russia's &lt;a href=\"http://howe.iki.rssi.ru/GCTC/gctc_e.htm\"&gt;Star City&lt;/a&gt;.",
pubDate: new Date("Tue, 03 Jun 2003 09:39:21 GMT")
}, {
id: "http://liftoff.msfc.nasa.gov/2003/05/30.html#item572",
description: "Sky watchers in Europe, Asia, and parts of Alaska and Canada will experience a &lt;a href=\"http://science.nasa.gov/headlines/y2003/30may_solareclipse.htm\"&gt;partial eclipse of the Sun&lt;/a&gt; on Saturday, May 31st.",
pubDate: new Date("Fri, 30 May 2003 11:06:42 GMT")
}, {
id: "http://liftoff.msfc.nasa.gov/2003/05/27.html#item571",
title: "The Engine That Does More",
link: "http://liftoff.msfc.nasa.gov/news/2003/news-VASIMR.asp",
description: "Before man travels to Mars, NASA hopes to design new engines that will let us fly through the Solar System more quickly. The proposed VASIMR engine would do that.",
pubDate: new Date("Tue, 27 May 2003 08:37:32 GMT")
}, {
id: "http://liftoff.msfc.nasa.gov/2003/05/20.html#item570",
title: "Astronauts' Dirty Laundry",
link: "http://liftoff.msfc.nasa.gov/news/2003/news-laundry.asp",
description: "Compared to earlier spacecraft, the International Space Station has many luxuries, but laundry facilities are not one of them. Instead, astronauts have other options.",
pubDate: new Date("Tue, 20 May 2003 08:56:02 GMT")
}]
};

View File

@@ -0,0 +1,18 @@
exports.name = "Atom (1.0)";
exports.file = "/Atom_Example.xml";
exports.expected = {
type: "atom",
id: "urn:uuid:60a76c80-d399-11d9-b91C-0003939e0af6",
title: "Example Feed",
link: "http://example.org/feed/",
description: "A subtitle.",
updated: new Date("2003-12-13T18:30:02Z"),
author: "johndoe@example.com",
items: [{
id: "urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a",
title: "Atom-Powered Robots Run Amok",
link: "http://example.org/2003/12/13/atom03",
description: "Some text.",
pubDate: new Date("2003-12-13T18:30:02Z")
}]
};

View File

@@ -0,0 +1,20 @@
exports.name = "RDF test";
exports.file = "/RDF_Example.xml";
exports.expected = {
"type": "rdf",
"id": "",
"title": "craigslist | all community in SF bay area",
"link": "http://sfbay.craigslist.org/ccc/",
"items": [
{
"title": "Music Equipment Repair and Consignment",
"link": "http://sfbay.craigslist.org/sby/muc/2681301534.html",
"description": "San Jose Rock Shop offers musical instrument repair and consignment! (408) 215-2065<br> <br> We are pleased to announce our NEW LOCATION: 1199 N 5th st. San Jose, ca 95112. Please call ahead, by appointment only.<br> <br> Recently featured by Metro Newspaper in their 2011 Best of the Silicon Valley edition see it online here:<br> <a href=\"http://www.metroactive.com/best-of-silicon-valley/2011/music-nightlife/editor-picks.html\" rel=\"nofollow\">http://www.metroactive.com/best-of-silicon-valley/2011/music-nightlife/editor-picks.html</a><br> <br> Guitar Set up (acoustic and electronic) $40!<!-- END CLTAGS -->"
},
{
"title": "Ride Offered - Oakland/BART to LA/SFV - TODAY 3PM 11/04 (oakland north / temescal)",
"link": "http://sfbay.craigslist.org/eby/rid/2685010755.html",
"description": "Im offering a lift for up to two people from Oakland (or near any BART station in the East Bay/580/880 Corridor, or San Jose/Morgan Hill, Gilroy) to the San Fernando Valley / Los Angeles area. Specifically, Im leaving from Oakland between 2:30 and 3:00pm (this is flexible, but if I leave too late my girlfriend will kill me), and heading to Woodland Hills via the 580, I-5, 405, and 101.<!-- END CLTAGS -->"
}
]
};

View File

@@ -0,0 +1,83 @@
{
"name": "Basic html",
"options": {},
"file": "Basic.html",
"expected": [
{
"event": "processinginstruction",
"data": [
"!doctype",
"!DOCTYPE html"
]
},
{
"event": "opentagname",
"data": [
"html"
]
},
{
"event": "opentag",
"data": [
"html",
{}
]
},
{
"event": "opentagname",
"data": [
"title"
]
},
{
"event": "opentag",
"data": [
"title",
{}
]
},
{
"event": "text",
"data": [
"The Title"
]
},
{
"event": "closetag",
"data": [
"title"
]
},
{
"event": "opentagname",
"data": [
"body"
]
},
{
"event": "opentag",
"data": [
"body",
{}
]
},
{
"event": "text",
"data": [
"Hello world"
]
},
{
"event": "closetag",
"data": [
"body"
]
},
{
"event": "closetag",
"data": [
"html"
]
}
]
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,644 @@
{
"name": "Atom feed",
"options": {"xmlMode": true},
"file": "Atom_Example.xml",
"expected": [
{
"event": "processinginstruction",
"data": [
"?xml",
"?xml version=\"1.0\" encoding=\"utf-8\"?"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "comment",
"data": [
" http://en.wikipedia.org/wiki/Atom_%28standard%29 "
]
},
{
"event": "commentend",
"data": []
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "opentagname",
"data": [
"feed"
]
},
{
"event": "attribute",
"data": [
"xmlns",
"http://www.w3.org/2005/Atom"
]
},
{
"event": "opentag",
"data": [
"feed",
{
"xmlns": "http://www.w3.org/2005/Atom"
}
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"title"
]
},
{
"event": "opentag",
"data": [
"title",
{}
]
},
{
"event": "text",
"data": [
"Example Feed"
]
},
{
"event": "closetag",
"data": [
"title"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"subtitle"
]
},
{
"event": "opentag",
"data": [
"subtitle",
{}
]
},
{
"event": "text",
"data": [
"A subtitle."
]
},
{
"event": "closetag",
"data": [
"subtitle"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"link"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.org/feed/"
]
},
{
"event": "attribute",
"data": [
"rel",
"self"
]
},
{
"event": "opentag",
"data": [
"link",
{
"href": "http://example.org/feed/",
"rel": "self"
}
]
},
{
"event": "closetag",
"data": [
"link"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"link"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.org/"
]
},
{
"event": "opentag",
"data": [
"link",
{
"href": "http://example.org/"
}
]
},
{
"event": "closetag",
"data": [
"link"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"id"
]
},
{
"event": "opentag",
"data": [
"id",
{}
]
},
{
"event": "text",
"data": [
"urn:uuid:60a76c80-d399-11d9-b91C-0003939e0af6"
]
},
{
"event": "closetag",
"data": [
"id"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"updated"
]
},
{
"event": "opentag",
"data": [
"updated",
{}
]
},
{
"event": "text",
"data": [
"2003-12-13T18:30:02Z"
]
},
{
"event": "closetag",
"data": [
"updated"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"author"
]
},
{
"event": "opentag",
"data": [
"author",
{}
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"name"
]
},
{
"event": "opentag",
"data": [
"name",
{}
]
},
{
"event": "text",
"data": [
"John Doe"
]
},
{
"event": "closetag",
"data": [
"name"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"email"
]
},
{
"event": "opentag",
"data": [
"email",
{}
]
},
{
"event": "text",
"data": [
"johndoe@example.com"
]
},
{
"event": "closetag",
"data": [
"email"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "closetag",
"data": [
"author"
]
},
{
"event": "text",
"data": [
"\n\n\t"
]
},
{
"event": "opentagname",
"data": [
"entry"
]
},
{
"event": "opentag",
"data": [
"entry",
{}
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"title"
]
},
{
"event": "opentag",
"data": [
"title",
{}
]
},
{
"event": "text",
"data": [
"Atom-Powered Robots Run Amok"
]
},
{
"event": "closetag",
"data": [
"title"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"link"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.org/2003/12/13/atom03"
]
},
{
"event": "opentag",
"data": [
"link",
{
"href": "http://example.org/2003/12/13/atom03"
}
]
},
{
"event": "closetag",
"data": [
"link"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"link"
]
},
{
"event": "attribute",
"data": [
"rel",
"alternate"
]
},
{
"event": "attribute",
"data": [
"type",
"text/html"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.org/2003/12/13/atom03.html"
]
},
{
"event": "opentag",
"data": [
"link",
{
"rel": "alternate",
"type": "text/html",
"href": "http://example.org/2003/12/13/atom03.html"
}
]
},
{
"event": "closetag",
"data": [
"link"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"link"
]
},
{
"event": "attribute",
"data": [
"rel",
"edit"
]
},
{
"event": "attribute",
"data": [
"href",
"http://example.org/2003/12/13/atom03/edit"
]
},
{
"event": "opentag",
"data": [
"link",
{
"rel": "edit",
"href": "http://example.org/2003/12/13/atom03/edit"
}
]
},
{
"event": "closetag",
"data": [
"link"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"id"
]
},
{
"event": "opentag",
"data": [
"id",
{}
]
},
{
"event": "text",
"data": [
"urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a"
]
},
{
"event": "closetag",
"data": [
"id"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"updated"
]
},
{
"event": "opentag",
"data": [
"updated",
{}
]
},
{
"event": "text",
"data": [
"2003-12-13T18:30:02Z"
]
},
{
"event": "closetag",
"data": [
"updated"
]
},
{
"event": "text",
"data": [
"\n\t\t"
]
},
{
"event": "opentagname",
"data": [
"summary"
]
},
{
"event": "opentag",
"data": [
"summary",
{}
]
},
{
"event": "text",
"data": [
"Some text."
]
},
{
"event": "closetag",
"data": [
"summary"
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "closetag",
"data": [
"entry"
]
},
{
"event": "text",
"data": [
"\n\n"
]
},
{
"event": "closetag",
"data": [
"feed"
]
}
]
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,354 @@
{
"name": "Attributes",
"options": {},
"file": "Attributes.html",
"expected": [
{
"event": "processinginstruction",
"data": [
"!doctype",
"!doctype html"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "opentagname",
"data": [
"html"
]
},
{
"event": "opentag",
"data": [
"html",
{}
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "opentagname",
"data": [
"head"
]
},
{
"event": "opentag",
"data": [
"head",
{}
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"title"
]
},
{
"event": "opentag",
"data": [
"title",
{}
]
},
{
"event": "text",
"data": [
"Attributes test"
]
},
{
"event": "closetag",
"data": [
"title"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "closetag",
"data": [
"head"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "opentagname",
"data": [
"body"
]
},
{
"event": "opentag",
"data": [
"body",
{}
]
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "comment",
"data": [
" Normal attributes "
]
},
{
"event": "commentend",
"data": []
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"button"
]
},
{
"event": "attribute",
"data": [
"id",
"test0"
]
},
{
"event": "attribute",
"data": [
"class",
"value0"
]
},
{
"event": "attribute",
"data": [
"title",
"value1"
]
},
{
"event": "opentag",
"data": [
"button",
{
"id": "test0",
"class": "value0",
"title": "value1"
}
]
},
{
"event": "text",
"data": [
"class=\"value0\" title=\"value1\""
]
},
{
"event": "closetag",
"data": [
"button"
]
},
{
"event": "text",
"data": [
"\n\n\t"
]
},
{
"event": "comment",
"data": [
" Attributes with no quotes or value "
]
},
{
"event": "commentend",
"data": []
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"button"
]
},
{
"event": "attribute",
"data": [
"id",
"test1"
]
},
{
"event": "attribute",
"data": [
"class",
"value2"
]
},
{
"event": "attribute",
"data": [
"disabled",
""
]
},
{
"event": "opentag",
"data": [
"button",
{
"id": "test1",
"class": "value2",
"disabled": ""
}
]
},
{
"event": "text",
"data": [
"class=value2 disabled"
]
},
{
"event": "closetag",
"data": [
"button"
]
},
{
"event": "text",
"data": [
"\n\n\t"
]
},
{
"event": "comment",
"data": [
" Attributes with no space between them. No valid, but accepted by the browser "
]
},
{
"event": "commentend",
"data": []
},
{
"event": "text",
"data": [
"\n\t"
]
},
{
"event": "opentagname",
"data": [
"button"
]
},
{
"event": "attribute",
"data": [
"id",
"test2"
]
},
{
"event": "attribute",
"data": [
"class",
"value4"
]
},
{
"event": "attribute",
"data": [
"title",
"value5"
]
},
{
"event": "opentag",
"data": [
"button",
{
"id": "test2",
"class": "value4",
"title": "value5"
}
]
},
{
"event": "text",
"data": [
"class=\"value4\"title=\"value5\""
]
},
{
"event": "closetag",
"data": [
"button"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "closetag",
"data": [
"body"
]
},
{
"event": "text",
"data": [
"\n"
]
},
{
"event": "closetag",
"data": [
"html"
]
}
]
}

View File

@@ -0,0 +1,81 @@
var htmlparser2 = require(".."),
fs = require("fs"),
path = require("path"),
assert = require("assert"),
Parser = htmlparser2.Parser,
CollectingHandler = htmlparser2.CollectingHandler;
exports.writeToParser = function(handler, options, data){
var parser = new Parser(handler, options);
//first, try to run the test via chunks
for(var i = 0; i < data.length; i++){
parser.write(data.charAt(i));
}
parser.end();
//then parse everything
parser.parseComplete(data);
};
//returns a tree structure
exports.getEventCollector = function(cb){
var handler = new CollectingHandler({onerror: cb, onend: function(){
cb(null, handler.events.reduce(eventReducer, []));
}});
return handler;
};
function eventReducer(events, arr){
if(arr[0] === "onerror" || arr[0] === "onend");
else if(arr[0] === "ontext" && events.length && events[events.length-1].event === "text"){
events[events.length-1].data[0] += arr[1];
} else {
events.push({
event: arr[0].substr(2),
data: arr.slice(1)
});
}
return events;
}
function getCallback(expected, done){
var repeated = false;
return function(err, actual){
assert.ifError(err);
try {
assert.deepEqual(expected, actual, "didn't get expected output");
} catch(e){
e.expected = JSON.stringify(expected, null, 2);
e.actual = JSON.stringify(actual, null, 2);
throw e;
}
if(repeated) done();
else repeated = true;
};
}
exports.mochaTest = function(name, root, test){
describe(name, readDir);
function readDir(cb){
var dir = path.join(root, name);
fs
.readdirSync(dir)
.filter(RegExp.prototype.test, /^[^\._]/) //ignore all files with a leading dot or underscore
.map(function(name){
return path.join(dir, name);
})
.map(require)
.forEach(runTest);
}
function runTest(file){
it(file.name, function(done){
test(file, getCallback(file.expected, done));
});
}
};