diff options
Diffstat (limited to 'node_modules/sax')
| -rw-r--r-- | node_modules/sax/LICENSE | 41 | ||||
| -rw-r--r-- | node_modules/sax/README.md | 225 | ||||
| -rw-r--r-- | node_modules/sax/lib/sax.js | 1565 | ||||
| -rw-r--r-- | node_modules/sax/package.json | 61 |
4 files changed, 1892 insertions, 0 deletions
diff --git a/node_modules/sax/LICENSE b/node_modules/sax/LICENSE new file mode 100644 index 0000000..ccffa08 --- /dev/null +++ b/node_modules/sax/LICENSE @@ -0,0 +1,41 @@ +The ISC License + +Copyright (c) Isaac Z. Schlueter and Contributors + +Permission to use, copy, modify, and/or distribute this software for any +purpose with or without fee is hereby granted, provided that the above +copyright notice and this permission notice appear in all copies. + +THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES +WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR +ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN +ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR +IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + +==== + +`String.fromCodePoint` by Mathias Bynens used according to terms of MIT +License, as follows: + + Copyright Mathias Bynens <https://mathiasbynens.be/> + + 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. diff --git a/node_modules/sax/README.md b/node_modules/sax/README.md new file mode 100644 index 0000000..afcd3f3 --- /dev/null +++ b/node_modules/sax/README.md @@ -0,0 +1,225 @@ +# sax js + +A sax-style parser for XML and HTML. + +Designed with [node](http://nodejs.org/) in mind, but should work fine in +the browser or other CommonJS implementations. + +## What This Is + +* A very simple tool to parse through an XML string. +* A stepping stone to a streaming HTML parser. +* A handy way to deal with RSS and other mostly-ok-but-kinda-broken XML + docs. + +## What This Is (probably) Not + +* An HTML Parser - That's a fine goal, but this isn't it. It's just + XML. +* A DOM Builder - You can use it to build an object model out of XML, + but it doesn't do that out of the box. +* XSLT - No DOM = no querying. +* 100% Compliant with (some other SAX implementation) - Most SAX + implementations are in Java and do a lot more than this does. +* An XML Validator - It does a little validation when in strict mode, but + not much. +* A Schema-Aware XSD Thing - Schemas are an exercise in fetishistic + masochism. +* A DTD-aware Thing - Fetching DTDs is a much bigger job. + +## Regarding `<!DOCTYPE`s and `<!ENTITY`s + +The parser will handle the basic XML entities in text nodes and attribute +values: `& < > ' "`. It's possible to define additional +entities in XML by putting them in the DTD. This parser doesn't do anything +with that. If you want to listen to the `ondoctype` event, and then fetch +the doctypes, and read the entities and add them to `parser.ENTITIES`, then +be my guest. + +Unknown entities will fail in strict mode, and in loose mode, will pass +through unmolested. + +## Usage + +```javascript +var sax = require("./lib/sax"), + strict = true, // set to false for html-mode + parser = sax.parser(strict); + +parser.onerror = function (e) { + // an error happened. +}; +parser.ontext = function (t) { + // got some text. t is the string of text. +}; +parser.onopentag = function (node) { + // opened a tag. node has "name" and "attributes" +}; +parser.onattribute = function (attr) { + // an attribute. attr has "name" and "value" +}; +parser.onend = function () { + // parser stream is done, and ready to have more stuff written to it. +}; + +parser.write('<xml>Hello, <who name="world">world</who>!</xml>').close(); + +// stream usage +// takes the same options as the parser +var saxStream = require("sax").createStream(strict, options) +saxStream.on("error", function (e) { + // unhandled errors will throw, since this is a proper node + // event emitter. + console.error("error!", e) + // clear the error + this._parser.error = null + this._parser.resume() +}) +saxStream.on("opentag", function (node) { + // same object as above +}) +// pipe is supported, and it's readable/writable +// same chunks coming in also go out. +fs.createReadStream("file.xml") + .pipe(saxStream) + .pipe(fs.createWriteStream("file-copy.xml")) +``` + + +## Arguments + +Pass the following arguments to the parser function. All are optional. + +`strict` - Boolean. Whether or not to be a jerk. Default: `false`. + +`opt` - Object bag of settings regarding string formatting. All default to `false`. + +Settings supported: + +* `trim` - Boolean. Whether or not to trim text and comment nodes. +* `normalize` - Boolean. If true, then turn any whitespace into a single + space. +* `lowercase` - Boolean. If true, then lowercase tag names and attribute names + in loose mode, rather than uppercasing them. +* `xmlns` - Boolean. If true, then namespaces are supported. +* `position` - Boolean. If false, then don't track line/col/position. +* `strictEntities` - Boolean. If true, only parse [predefined XML + entities](http://www.w3.org/TR/REC-xml/#sec-predefined-ent) + (`&`, `'`, `>`, `<`, and `"`) + +## Methods + +`write` - Write bytes onto the stream. You don't have to do this all at +once. You can keep writing as much as you want. + +`close` - Close the stream. Once closed, no more data may be written until +it is done processing the buffer, which is signaled by the `end` event. + +`resume` - To gracefully handle errors, assign a listener to the `error` +event. Then, when the error is taken care of, you can call `resume` to +continue parsing. Otherwise, the parser will not continue while in an error +state. + +## Members + +At all times, the parser object will have the following members: + +`line`, `column`, `position` - Indications of the position in the XML +document where the parser currently is looking. + +`startTagPosition` - Indicates the position where the current tag starts. + +`closed` - Boolean indicating whether or not the parser can be written to. +If it's `true`, then wait for the `ready` event to write again. + +`strict` - Boolean indicating whether or not the parser is a jerk. + +`opt` - Any options passed into the constructor. + +`tag` - The current tag being dealt with. + +And a bunch of other stuff that you probably shouldn't touch. + +## Events + +All events emit with a single argument. To listen to an event, assign a +function to `on<eventname>`. Functions get executed in the this-context of +the parser object. The list of supported events are also in the exported +`EVENTS` array. + +When using the stream interface, assign handlers using the EventEmitter +`on` function in the normal fashion. + +`error` - Indication that something bad happened. The error will be hanging +out on `parser.error`, and must be deleted before parsing can continue. By +listening to this event, you can keep an eye on that kind of stuff. Note: +this happens *much* more in strict mode. Argument: instance of `Error`. + +`text` - Text node. Argument: string of text. + +`doctype` - The `<!DOCTYPE` declaration. Argument: doctype string. + +`processinginstruction` - Stuff like `<?xml foo="blerg" ?>`. Argument: +object with `name` and `body` members. Attributes are not parsed, as +processing instructions have implementation dependent semantics. + +`sgmldeclaration` - Random SGML declarations. Stuff like `<!ENTITY p>` +would trigger this kind of event. This is a weird thing to support, so it +might go away at some point. SAX isn't intended to be used to parse SGML, +after all. + +`opentagstart` - Emitted immediately when the tag name is available, +but before any attributes are encountered. Argument: object with a +`name` field and an empty `attributes` set. Note that this is the +same object that will later be emitted in the `opentag` event. + +`opentag` - An opening tag. Argument: object with `name` and `attributes`. +In non-strict mode, tag names are uppercased, unless the `lowercase` +option is set. If the `xmlns` option is set, then it will contain +namespace binding information on the `ns` member, and will have a +`local`, `prefix`, and `uri` member. + +`closetag` - A closing tag. In loose mode, tags are auto-closed if their +parent closes. In strict mode, well-formedness is enforced. Note that +self-closing tags will have `closeTag` emitted immediately after `openTag`. +Argument: tag name. + +`attribute` - An attribute node. Argument: object with `name` and `value`. +In non-strict mode, attribute names are uppercased, unless the `lowercase` +option is set. If the `xmlns` option is set, it will also contains namespace +information. + +`comment` - A comment node. Argument: the string of the comment. + +`opencdata` - The opening tag of a `<![CDATA[` block. + +`cdata` - The text of a `<![CDATA[` block. Since `<![CDATA[` blocks can get +quite large, this event may fire multiple times for a single block, if it +is broken up into multiple `write()`s. Argument: the string of random +character data. + +`closecdata` - The closing tag (`]]>`) of a `<![CDATA[` block. + +`opennamespace` - If the `xmlns` option is set, then this event will +signal the start of a new namespace binding. + +`closenamespace` - If the `xmlns` option is set, then this event will +signal the end of a namespace binding. + +`end` - Indication that the closed stream has ended. + +`ready` - Indication that the stream has reset, and is ready to be written +to. + +`noscript` - In non-strict mode, `<script>` tags trigger a `"script"` +event, and their contents are not checked for special xml characters. +If you pass `noscript: true`, then this behavior is suppressed. + +## Reporting Problems + +It's best to write a failing test if you find an issue. I will always +accept pull requests with failing tests if they demonstrate intended +behavior, but it is very hard to figure out what issue you're describing +without a test. Writing a test is also the best way for you yourself +to figure out if you really understand the issue you think you have with +sax-js. diff --git a/node_modules/sax/lib/sax.js b/node_modules/sax/lib/sax.js new file mode 100644 index 0000000..795d607 --- /dev/null +++ b/node_modules/sax/lib/sax.js @@ -0,0 +1,1565 @@ +;(function (sax) { // wrapper for non-node envs + sax.parser = function (strict, opt) { return new SAXParser(strict, opt) } + sax.SAXParser = SAXParser + sax.SAXStream = SAXStream + sax.createStream = createStream + + // When we pass the MAX_BUFFER_LENGTH position, start checking for buffer overruns. + // When we check, schedule the next check for MAX_BUFFER_LENGTH - (max(buffer lengths)), + // since that's the earliest that a buffer overrun could occur. This way, checks are + // as rare as required, but as often as necessary to ensure never crossing this bound. + // Furthermore, buffers are only tested at most once per write(), so passing a very + // large string into write() might have undesirable effects, but this is manageable by + // the caller, so it is assumed to be safe. Thus, a call to write() may, in the extreme + // edge case, result in creating at most one complete copy of the string passed in. + // Set to Infinity to have unlimited buffers. + sax.MAX_BUFFER_LENGTH = 64 * 1024 + + var buffers = [ + 'comment', 'sgmlDecl', 'textNode', 'tagName', 'doctype', + 'procInstName', 'procInstBody', 'entity', 'attribName', + 'attribValue', 'cdata', 'script' + ] + + sax.EVENTS = [ + 'text', + 'processinginstruction', + 'sgmldeclaration', + 'doctype', + 'comment', + 'opentagstart', + 'attribute', + 'opentag', + 'closetag', + 'opencdata', + 'cdata', + 'closecdata', + 'error', + 'end', + 'ready', + 'script', + 'opennamespace', + 'closenamespace' + ] + + function SAXParser (strict, opt) { + if (!(this instanceof SAXParser)) { + return new SAXParser(strict, opt) + } + + var parser = this + clearBuffers(parser) + parser.q = parser.c = '' + parser.bufferCheckPosition = sax.MAX_BUFFER_LENGTH + parser.opt = opt || {} + parser.opt.lowercase = parser.opt.lowercase || parser.opt.lowercasetags + parser.looseCase = parser.opt.lowercase ? 'toLowerCase' : 'toUpperCase' + parser.tags = [] + parser.closed = parser.closedRoot = parser.sawRoot = false + parser.tag = parser.error = null + parser.strict = !!strict + parser.noscript = !!(strict || parser.opt.noscript) + parser.state = S.BEGIN + parser.strictEntities = parser.opt.strictEntities + parser.ENTITIES = parser.strictEntities ? Object.create(sax.XML_ENTITIES) : Object.create(sax.ENTITIES) + parser.attribList = [] + + // namespaces form a prototype chain. + // it always points at the current tag, + // which protos to its parent tag. + if (parser.opt.xmlns) { + parser.ns = Object.create(rootNS) + } + + // mostly just for error reporting + parser.trackPosition = parser.opt.position !== false + if (parser.trackPosition) { + parser.position = parser.line = parser.column = 0 + } + emit(parser, 'onready') + } + + if (!Object.create) { + Object.create = function (o) { + function F () {} + F.prototype = o + var newf = new F() + return newf + } + } + + if (!Object.keys) { + Object.keys = function (o) { + var a = [] + for (var i in o) if (o.hasOwnProperty(i)) a.push(i) + return a + } + } + + function checkBufferLength (parser) { + var maxAllowed = Math.max(sax.MAX_BUFFER_LENGTH, 10) + var maxActual = 0 + for (var i = 0, l = buffers.length; i < l; i++) { + var len = parser[buffers[i]].length + if (len > maxAllowed) { + // Text/cdata nodes can get big, and since they're buffered, + // we can get here under normal conditions. + // Avoid issues by emitting the text node now, + // so at least it won't get any bigger. + switch (buffers[i]) { + case 'textNode': + closeText(parser) + break + + case 'cdata': + emitNode(parser, 'oncdata', parser.cdata) + parser.cdata = '' + break + + case 'script': + emitNode(parser, 'onscript', parser.script) + parser.script = '' + break + + default: + error(parser, 'Max buffer length exceeded: ' + buffers[i]) + } + } + maxActual = Math.max(maxActual, len) + } + // schedule the next check for the earliest possible buffer overrun. + var m = sax.MAX_BUFFER_LENGTH - maxActual + parser.bufferCheckPosition = m + parser.position + } + + function clearBuffers (parser) { + for (var i = 0, l = buffers.length; i < l; i++) { + parser[buffers[i]] = '' + } + } + + function flushBuffers (parser) { + closeText(parser) + if (parser.cdata !== '') { + emitNode(parser, 'oncdata', parser.cdata) + parser.cdata = '' + } + if (parser.script !== '') { + emitNode(parser, 'onscript', parser.script) + parser.script = '' + } + } + + SAXParser.prototype = { + end: function () { end(this) }, + write: write, + resume: function () { this.error = null; return this }, + close: function () { return this.write(null) }, + flush: function () { flushBuffers(this) } + } + + var Stream + try { + Stream = require('stream').Stream + } catch (ex) { + Stream = function () {} + } + + var streamWraps = sax.EVENTS.filter(function (ev) { + return ev !== 'error' && ev !== 'end' + }) + + function createStream (strict, opt) { + return new SAXStream(strict, opt) + } + + function SAXStream (strict, opt) { + if (!(this instanceof SAXStream)) { + return new SAXStream(strict, opt) + } + + Stream.apply(this) + + this._parser = new SAXParser(strict, opt) + this.writable = true + this.readable = true + + var me = this + + this._parser.onend = function () { + me.emit('end') + } + + this._parser.onerror = function (er) { + me.emit('error', er) + + // if didn't throw, then means error was handled. + // go ahead and clear error, so we can write again. + me._parser.error = null + } + + this._decoder = null + + streamWraps.forEach(function (ev) { + Object.defineProperty(me, 'on' + ev, { + get: function () { + return me._parser['on' + ev] + }, + set: function (h) { + if (!h) { + me.removeAllListeners(ev) + me._parser['on' + ev] = h + return h + } + me.on(ev, h) + }, + enumerable: true, + configurable: false + }) + }) + } + + SAXStream.prototype = Object.create(Stream.prototype, { + constructor: { + value: SAXStream + } + }) + + SAXStream.prototype.write = function (data) { + if (typeof Buffer === 'function' && + typeof Buffer.isBuffer === 'function' && + Buffer.isBuffer(data)) { + if (!this._decoder) { + var SD = require('string_decoder').StringDecoder + this._decoder = new SD('utf8') + } + data = this._decoder.write(data) + } + + this._parser.write(data.toString()) + this.emit('data', data) + return true + } + + SAXStream.prototype.end = function (chunk) { + if (chunk && chunk.length) { + this.write(chunk) + } + this._parser.end() + return true + } + + SAXStream.prototype.on = function (ev, handler) { + var me = this + if (!me._parser['on' + ev] && streamWraps.indexOf(ev) !== -1) { + me._parser['on' + ev] = function () { + var args = arguments.length === 1 ? [arguments[0]] : Array.apply(null, arguments) + args.splice(0, 0, ev) + me.emit.apply(me, args) + } + } + + return Stream.prototype.on.call(me, ev, handler) + } + + // this really needs to be replaced with character classes. + // XML allows all manner of ridiculous numbers and digits. + var CDATA = '[CDATA[' + var DOCTYPE = 'DOCTYPE' + var XML_NAMESPACE = 'http://www.w3.org/XML/1998/namespace' + var XMLNS_NAMESPACE = 'http://www.w3.org/2000/xmlns/' + var rootNS = { xml: XML_NAMESPACE, xmlns: XMLNS_NAMESPACE } + + // http://www.w3.org/TR/REC-xml/#NT-NameStartChar + // This implementation works on strings, a single character at a time + // as such, it cannot ever support astral-plane characters (10000-EFFFF) + // without a significant breaking change to either this parser, or the + // JavaScript language. Implementation of an emoji-capable xml parser + // is left as an exercise for the reader. + var nameStart = /[:_A-Za-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]/ + + var nameBody = /[:_A-Za-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\u00B7\u0300-\u036F\u203F-\u2040.\d-]/ + + var entityStart = /[#:_A-Za-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]/ + var entityBody = /[#:_A-Za-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\u00B7\u0300-\u036F\u203F-\u2040.\d-]/ + + function isWhitespace (c) { + return c === ' ' || c === '\n' || c === '\r' || c === '\t' + } + + function isQuote (c) { + return c === '"' || c === '\'' + } + + function isAttribEnd (c) { + return c === '>' || isWhitespace(c) + } + + function isMatch (regex, c) { + return regex.test(c) + } + + function notMatch (regex, c) { + return !isMatch(regex, c) + } + + var S = 0 + sax.STATE = { + BEGIN: S++, // leading byte order mark or whitespace + BEGIN_WHITESPACE: S++, // leading whitespace + TEXT: S++, // general stuff + TEXT_ENTITY: S++, // & and such. + OPEN_WAKA: S++, // < + SGML_DECL: S++, // <!BLARG + SGML_DECL_QUOTED: S++, // <!BLARG foo "bar + DOCTYPE: S++, // <!DOCTYPE + DOCTYPE_QUOTED: S++, // <!DOCTYPE "//blah + DOCTYPE_DTD: S++, // <!DOCTYPE "//blah" [ ... + DOCTYPE_DTD_QUOTED: S++, // <!DOCTYPE "//blah" [ "foo + COMMENT_STARTING: S++, // <!- + COMMENT: S++, // <!-- + COMMENT_ENDING: S++, // <!-- blah - + COMMENT_ENDED: S++, // <!-- blah -- + CDATA: S++, // <![CDATA[ something + CDATA_ENDING: S++, // ] + CDATA_ENDING_2: S++, // ]] + PROC_INST: S++, // <?hi + PROC_INST_BODY: S++, // <?hi there + PROC_INST_ENDING: S++, // <?hi "there" ? + OPEN_TAG: S++, // <strong + OPEN_TAG_SLASH: S++, // <strong / + ATTRIB: S++, // <a + ATTRIB_NAME: S++, // <a foo + ATTRIB_NAME_SAW_WHITE: S++, // <a foo _ + ATTRIB_VALUE: S++, // <a foo= + ATTRIB_VALUE_QUOTED: S++, // <a foo="bar + ATTRIB_VALUE_CLOSED: S++, // <a foo="bar" + ATTRIB_VALUE_UNQUOTED: S++, // <a foo=bar + ATTRIB_VALUE_ENTITY_Q: S++, // <foo bar=""" + ATTRIB_VALUE_ENTITY_U: S++, // <foo bar=" + CLOSE_TAG: S++, // </a + CLOSE_TAG_SAW_WHITE: S++, // </a > + SCRIPT: S++, // <script> ... + SCRIPT_ENDING: S++ // <script> ... < + } + + sax.XML_ENTITIES = { + 'amp': '&', + 'gt': '>', + 'lt': '<', + 'quot': '"', + 'apos': "'" + } + + sax.ENTITIES = { + 'amp': '&', + 'gt': '>', + 'lt': '<', + 'quot': '"', + 'apos': "'", + 'AElig': 198, + 'Aacute': 193, + 'Acirc': 194, + 'Agrave': 192, + 'Aring': 197, + 'Atilde': 195, + 'Auml': 196, + 'Ccedil': 199, + 'ETH': 208, + 'Eacute': 201, + 'Ecirc': 202, + 'Egrave': 200, + 'Euml': 203, + 'Iacute': 205, + 'Icirc': 206, + 'Igrave': 204, + 'Iuml': 207, + 'Ntilde': 209, + 'Oacute': 211, + 'Ocirc': 212, + 'Ograve': 210, + 'Oslash': 216, + 'Otilde': 213, + 'Ouml': 214, + 'THORN': 222, + 'Uacute': 218, + 'Ucirc': 219, + 'Ugrave': 217, + 'Uuml': 220, + 'Yacute': 221, + 'aacute': 225, + 'acirc': 226, + 'aelig': 230, + 'agrave': 224, + 'aring': 229, + 'atilde': 227, + 'auml': 228, + 'ccedil': 231, + 'eacute': 233, + 'ecirc': 234, + 'egrave': 232, + 'eth': 240, + 'euml': 235, + 'iacute': 237, + 'icirc': 238, + 'igrave': 236, + 'iuml': 239, + 'ntilde': 241, + 'oacute': 243, + 'ocirc': 244, + 'ograve': 242, + 'oslash': 248, + 'otilde': 245, + 'ouml': 246, + 'szlig': 223, + 'thorn': 254, + 'uacute': 250, + 'ucirc': 251, + 'ugrave': 249, + 'uuml': 252, + 'yacute': 253, + 'yuml': 255, + 'copy': 169, + 'reg': 174, + 'nbsp': 160, + 'iexcl': 161, + 'cent': 162, + 'pound': 163, + 'curren': 164, + 'yen': 165, + 'brvbar': 166, + 'sect': 167, + 'uml': 168, + 'ordf': 170, + 'laquo': 171, + 'not': 172, + 'shy': 173, + 'macr': 175, + 'deg': 176, + 'plusmn': 177, + 'sup1': 185, + 'sup2': 178, + 'sup3': 179, + 'acute': 180, + 'micro': 181, + 'para': 182, + 'middot': 183, + 'cedil': 184, + 'ordm': 186, + 'raquo': 187, + 'frac14': 188, + 'frac12': 189, + 'frac34': 190, + 'iquest': 191, + 'times': 215, + 'divide': 247, + 'OElig': 338, + 'oelig': 339, + 'Scaron': 352, + 'scaron': 353, + 'Yuml': 376, + 'fnof': 402, + 'circ': 710, + 'tilde': 732, + 'Alpha': 913, + 'Beta': 914, + 'Gamma': 915, + 'Delta': 916, + 'Epsilon': 917, + 'Zeta': 918, + 'Eta': 919, + 'Theta': 920, + 'Iota': 921, + 'Kappa': 922, + 'Lambda': 923, + 'Mu': 924, + 'Nu': 925, + 'Xi': 926, + 'Omicron': 927, + 'Pi': 928, + 'Rho': 929, + 'Sigma': 931, + 'Tau': 932, + 'Upsilon': 933, + 'Phi': 934, + 'Chi': 935, + 'Psi': 936, + 'Omega': 937, + 'alpha': 945, + 'beta': 946, + 'gamma': 947, + 'delta': 948, + 'epsilon': 949, + 'zeta': 950, + 'eta': 951, + 'theta': 952, + 'iota': 953, + 'kappa': 954, + 'lambda': 955, + 'mu': 956, + 'nu': 957, + 'xi': 958, + 'omicron': 959, + 'pi': 960, + 'rho': 961, + 'sigmaf': 962, + 'sigma': 963, + 'tau': 964, + 'upsilon': 965, + 'phi': 966, + 'chi': 967, + 'psi': 968, + 'omega': 969, + 'thetasym': 977, + 'upsih': 978, + 'piv': 982, + 'ensp': 8194, + 'emsp': 8195, + 'thinsp': 8201, + 'zwnj': 8204, + 'zwj': 8205, + 'lrm': 8206, + 'rlm': 8207, + 'ndash': 8211, + 'mdash': 8212, + 'lsquo': 8216, + 'rsquo': 8217, + 'sbquo': 8218, + 'ldquo': 8220, + 'rdquo': 8221, + 'bdquo': 8222, + 'dagger': 8224, + 'Dagger': 8225, + 'bull': 8226, + 'hellip': 8230, + 'permil': 8240, + 'prime': 8242, + 'Prime': 8243, + 'lsaquo': 8249, + 'rsaquo': 8250, + 'oline': 8254, + 'frasl': 8260, + 'euro': 8364, + 'image': 8465, + 'weierp': 8472, + 'real': 8476, + 'trade': 8482, + 'alefsym': 8501, + 'larr': 8592, + 'uarr': 8593, + 'rarr': 8594, + 'darr': 8595, + 'harr': 8596, + 'crarr': 8629, + 'lArr': 8656, + 'uArr': 8657, + 'rArr': 8658, + 'dArr': 8659, + 'hArr': 8660, + 'forall': 8704, + 'part': 8706, + 'exist': 8707, + 'empty': 8709, + 'nabla': 8711, + 'isin': 8712, + 'notin': 8713, + 'ni': 8715, + 'prod': 8719, + 'sum': 8721, + 'minus': 8722, + 'lowast': 8727, + 'radic': 8730, + 'prop': 8733, + 'infin': 8734, + 'ang': 8736, + 'and': 8743, + 'or': 8744, + 'cap': 8745, + 'cup': 8746, + 'int': 8747, + 'there4': 8756, + 'sim': 8764, + 'cong': 8773, + 'asymp': 8776, + 'ne': 8800, + 'equiv': 8801, + 'le': 8804, + 'ge': 8805, + 'sub': 8834, + 'sup': 8835, + 'nsub': 8836, + 'sube': 8838, + 'supe': 8839, + 'oplus': 8853, + 'otimes': 8855, + 'perp': 8869, + 'sdot': 8901, + 'lceil': 8968, + 'rceil': 8969, + 'lfloor': 8970, + 'rfloor': 8971, + 'lang': 9001, + 'rang': 9002, + 'loz': 9674, + 'spades': 9824, + 'clubs': 9827, + 'hearts': 9829, + 'diams': 9830 + } + + Object.keys(sax.ENTITIES).forEach(function (key) { + var e = sax.ENTITIES[key] + var s = typeof e === 'number' ? String.fromCharCode(e) : e + sax.ENTITIES[key] = s + }) + + for (var s in sax.STATE) { + sax.STATE[sax.STATE[s]] = s + } + + // shorthand + S = sax.STATE + + function emit (parser, event, data) { + parser[event] && parser[event](data) + } + + function emitNode (parser, nodeType, data) { + if (parser.textNode) closeText(parser) + emit(parser, nodeType, data) + } + + function closeText (parser) { + parser.textNode = textopts(parser.opt, parser.textNode) + if (parser.textNode) emit(parser, 'ontext', parser.textNode) + parser.textNode = '' + } + + function textopts (opt, text) { + if (opt.trim) text = text.trim() + if (opt.normalize) text = text.replace(/\s+/g, ' ') + return text + } + + function error (parser, er) { + closeText(parser) + if (parser.trackPosition) { + er += '\nLine: ' + parser.line + + '\nColumn: ' + parser.column + + '\nChar: ' + parser.c + } + er = new Error(er) + parser.error = er + emit(parser, 'onerror', er) + return parser + } + + function end (parser) { + if (parser.sawRoot && !parser.closedRoot) strictFail(parser, 'Unclosed root tag') + if ((parser.state !== S.BEGIN) && + (parser.state !== S.BEGIN_WHITESPACE) && + (parser.state !== S.TEXT)) { + error(parser, 'Unexpected end') + } + closeText(parser) + parser.c = '' + parser.closed = true + emit(parser, 'onend') + SAXParser.call(parser, parser.strict, parser.opt) + return parser + } + + function strictFail (parser, message) { + if (typeof parser !== 'object' || !(parser instanceof SAXParser)) { + throw new Error('bad call to strictFail') + } + if (parser.strict) { + error(parser, message) + } + } + + function newTag (parser) { + if (!parser.strict) parser.tagName = parser.tagName[parser.looseCase]() + var parent = parser.tags[parser.tags.length - 1] || parser + var tag = parser.tag = { name: parser.tagName, attributes: {} } + + // will be overridden if tag contails an xmlns="foo" or xmlns:foo="bar" + if (parser.opt.xmlns) { + tag.ns = parent.ns + } + parser.attribList.length = 0 + emitNode(parser, 'onopentagstart', tag) + } + + function qname (name, attribute) { + var i = name.indexOf(':') + var qualName = i < 0 ? [ '', name ] : name.split(':') + var prefix = qualName[0] + var local = qualName[1] + + // <x "xmlns"="http://foo"> + if (attribute && name === 'xmlns') { + prefix = 'xmlns' + local = '' + } + + return { prefix: prefix, local: local } + } + + function attrib (parser) { + if (!parser.strict) { + parser.attribName = parser.attribName[parser.looseCase]() + } + + if (parser.attribList.indexOf(parser.attribName) !== -1 || + parser.tag.attributes.hasOwnProperty(parser.attribName)) { + parser.attribName = parser.attribValue = '' + return + } + + if (parser.opt.xmlns) { + var qn = qname(parser.attribName, true) + var prefix = qn.prefix + var local = qn.local + + if (prefix === 'xmlns') { + // namespace binding attribute. push the binding into scope + if (local === 'xml' && parser.attribValue !== XML_NAMESPACE) { + strictFail(parser, + 'xml: prefix must be bound to ' + XML_NAMESPACE + '\n' + + 'Actual: ' + parser.attribValue) + } else if (local === 'xmlns' && parser.attribValue !== XMLNS_NAMESPACE) { + strictFail(parser, + 'xmlns: prefix must be bound to ' + XMLNS_NAMESPACE + '\n' + + 'Actual: ' + parser.attribValue) + } else { + var tag = parser.tag + var parent = parser.tags[parser.tags.length - 1] || parser + if (tag.ns === parent.ns) { + tag.ns = Object.create(parent.ns) + } + tag.ns[local] = parser.attribValue + } + } + + // defer onattribute events until all attributes have been seen + // so any new bindings can take effect. preserve attribute order + // so deferred events can be emitted in document order + parser.attribList.push([parser.attribName, parser.attribValue]) + } else { + // in non-xmlns mode, we can emit the event right away + parser.tag.attributes[parser.attribName] = parser.attribValue + emitNode(parser, 'onattribute', { + name: parser.attribName, + value: parser.attribValue + }) + } + + parser.attribName = parser.attribValue = '' + } + + function openTag (parser, selfClosing) { + if (parser.opt.xmlns) { + // emit namespace binding events + var tag = parser.tag + + // add namespace info to tag + var qn = qname(parser.tagName) + tag.prefix = qn.prefix + tag.local = qn.local + tag.uri = tag.ns[qn.prefix] || '' + + if (tag.prefix && !tag.uri) { + strictFail(parser, 'Unbound namespace prefix: ' + + JSON.stringify(parser.tagName)) + tag.uri = qn.prefix + } + + var parent = parser.tags[parser.tags.length - 1] || parser + if (tag.ns && parent.ns !== tag.ns) { + Object.keys(tag.ns).forEach(function (p) { + emitNode(parser, 'onopennamespace', { + prefix: p, + uri: tag.ns[p] + }) + }) + } + + // handle deferred onattribute events + // Note: do not apply default ns to attributes: + // http://www.w3.org/TR/REC-xml-names/#defaulting + for (var i = 0, l = parser.attribList.length; i < l; i++) { + var nv = parser.attribList[i] + var name = nv[0] + var value = nv[1] + var qualName = qname(name, true) + var prefix = qualName.prefix + var local = qualName.local + var uri = prefix === '' ? '' : (tag.ns[prefix] || '') + var a = { + name: name, + value: value, + prefix: prefix, + local: local, + uri: uri + } + + // if there's any attributes with an undefined namespace, + // then fail on them now. + if (prefix && prefix !== 'xmlns' && !uri) { + strictFail(parser, 'Unbound namespace prefix: ' + + JSON.stringify(prefix)) + a.uri = prefix + } + parser.tag.attributes[name] = a + emitNode(parser, 'onattribute', a) + } + parser.attribList.length = 0 + } + + parser.tag.isSelfClosing = !!selfClosing + + // process the tag + parser.sawRoot = true + parser.tags.push(parser.tag) + emitNode(parser, 'onopentag', parser.tag) + if (!selfClosing) { + // special case for <script> in non-strict mode. + if (!parser.noscript && parser.tagName.toLowerCase() === 'script') { + parser.state = S.SCRIPT + } else { + parser.state = S.TEXT + } + parser.tag = null + parser.tagName = '' + } + parser.attribName = parser.attribValue = '' + parser.attribList.length = 0 + } + + function closeTag (parser) { + if (!parser.tagName) { + strictFail(parser, 'Weird empty close tag.') + parser.textNode += '</>' + parser.state = S.TEXT + return + } + + if (parser.script) { + if (parser.tagName !== 'script') { + parser.script += '</' + parser.tagName + '>' + parser.tagName = '' + parser.state = S.SCRIPT + return + } + emitNode(parser, 'onscript', parser.script) + parser.script = '' + } + + // first make sure that the closing tag actually exists. + // <a><b></c></b></a> will close everything, otherwise. + var t = parser.tags.length + var tagName = parser.tagName + if (!parser.strict) { + tagName = tagName[parser.looseCase]() + } + var closeTo = tagName + while (t--) { + var close = parser.tags[t] + if (close.name !== closeTo) { + // fail the first time in strict mode + strictFail(parser, 'Unexpected close tag') + } else { + break + } + } + + // didn't find it. we already failed for strict, so just abort. + if (t < 0) { + strictFail(parser, 'Unmatched closing tag: ' + parser.tagName) + parser.textNode += '</' + parser.tagName + '>' + parser.state = S.TEXT + return + } + parser.tagName = tagName + var s = parser.tags.length + while (s-- > t) { + var tag = parser.tag = parser.tags.pop() + parser.tagName = parser.tag.name + emitNode(parser, 'onclosetag', parser.tagName) + + var x = {} + for (var i in tag.ns) { + x[i] = tag.ns[i] + } + + var parent = parser.tags[parser.tags.length - 1] || parser + if (parser.opt.xmlns && tag.ns !== parent.ns) { + // remove namespace bindings introduced by tag + Object.keys(tag.ns).forEach(function (p) { + var n = tag.ns[p] + emitNode(parser, 'onclosenamespace', { prefix: p, uri: n }) + }) + } + } + if (t === 0) parser.closedRoot = true + parser.tagName = parser.attribValue = parser.attribName = '' + parser.attribList.length = 0 + parser.state = S.TEXT + } + + function parseEntity (parser) { + var entity = parser.entity + var entityLC = entity.toLowerCase() + var num + var numStr = '' + + if (parser.ENTITIES[entity]) { + return parser.ENTITIES[entity] + } + if (parser.ENTITIES[entityLC]) { + return parser.ENTITIES[entityLC] + } + entity = entityLC + if (entity.charAt(0) === '#') { + if (entity.charAt(1) === 'x') { + entity = entity.slice(2) + num = parseInt(entity, 16) + numStr = num.toString(16) + } else { + entity = entity.slice(1) + num = parseInt(entity, 10) + numStr = num.toString(10) + } + } + entity = entity.replace(/^0+/, '') + if (isNaN(num) || numStr.toLowerCase() !== entity) { + strictFail(parser, 'Invalid character entity') + return '&' + parser.entity + ';' + } + + return String.fromCodePoint(num) + } + + function beginWhiteSpace (parser, c) { + if (c === '<') { + parser.state = S.OPEN_WAKA + parser.startTagPosition = parser.position + } else if (!isWhitespace(c)) { + // have to process this as a text node. + // weird, but happens. + strictFail(parser, 'Non-whitespace before first tag.') + parser.textNode = c + parser.state = S.TEXT + } + } + + function charAt (chunk, i) { + var result = '' + if (i < chunk.length) { + result = chunk.charAt(i) + } + return result + } + + function write (chunk) { + var parser = this + if (this.error) { + throw this.error + } + if (parser.closed) { + return error(parser, + 'Cannot write after close. Assign an onready handler.') + } + if (chunk === null) { + return end(parser) + } + if (typeof chunk === 'object') { + chunk = chunk.toString() + } + var i = 0 + var c = '' + while (true) { + c = charAt(chunk, i++) + parser.c = c + + if (!c) { + break + } + + if (parser.trackPosition) { + parser.position++ + if (c === '\n') { + parser.line++ + parser.column = 0 + } else { + parser.column++ + } + } + + switch (parser.state) { + case S.BEGIN: + parser.state = S.BEGIN_WHITESPACE + if (c === '\uFEFF') { + continue + } + beginWhiteSpace(parser, c) + continue + + case S.BEGIN_WHITESPACE: + beginWhiteSpace(parser, c) + continue + + case S.TEXT: + if (parser.sawRoot && !parser.closedRoot) { + var starti = i - 1 + while (c && c !== '<' && c !== '&') { + c = charAt(chunk, i++) + if (c && parser.trackPosition) { + parser.position++ + if (c === '\n') { + parser.line++ + parser.column = 0 + } else { + parser.column++ + } + } + } + parser.textNode += chunk.substring(starti, i - 1) + } + if (c === '<' && !(parser.sawRoot && parser.closedRoot && !parser.strict)) { + parser.state = S.OPEN_WAKA + parser.startTagPosition = parser.position + } else { + if (!isWhitespace(c) && (!parser.sawRoot || parser.closedRoot)) { + strictFail(parser, 'Text data outside of root node.') + } + if (c === '&') { + parser.state = S.TEXT_ENTITY + } else { + parser.textNode += c + } + } + continue + + case S.SCRIPT: + // only non-strict + if (c === '<') { + parser.state = S.SCRIPT_ENDING + } else { + parser.script += c + } + continue + + case S.SCRIPT_ENDING: + if (c === '/') { + parser.state = S.CLOSE_TAG + } else { + parser.script += '<' + c + parser.state = S.SCRIPT + } + continue + + case S.OPEN_WAKA: + // either a /, ?, !, or text is coming next. + if (c === '!') { + parser.state = S.SGML_DECL + parser.sgmlDecl = '' + } else if (isWhitespace(c)) { + // wait for it... + } else if (isMatch(nameStart, c)) { + parser.state = S.OPEN_TAG + parser.tagName = c + } else if (c === '/') { + parser.state = S.CLOSE_TAG + parser.tagName = '' + } else if (c === '?') { + parser.state = S.PROC_INST + parser.procInstName = parser.procInstBody = '' + } else { + strictFail(parser, 'Unencoded <') + // if there was some whitespace, then add that in. + if (parser.startTagPosition + 1 < parser.position) { + var pad = parser.position - parser.startTagPosition + c = new Array(pad).join(' ') + c + } + parser.textNode += '<' + c + parser.state = S.TEXT + } + continue + + case S.SGML_DECL: + if ((parser.sgmlDecl + c).toUpperCase() === CDATA) { + emitNode(parser, 'onopencdata') + parser.state = S.CDATA + parser.sgmlDecl = '' + parser.cdata = '' + } else if (parser.sgmlDecl + c === '--') { + parser.state = S.COMMENT + parser.comment = '' + parser.sgmlDecl = '' + } else if ((parser.sgmlDecl + c).toUpperCase() === DOCTYPE) { + parser.state = S.DOCTYPE + if (parser.doctype || parser.sawRoot) { + strictFail(parser, + 'Inappropriately located doctype declaration') + } + parser.doctype = '' + parser.sgmlDecl = '' + } else if (c === '>') { + emitNode(parser, 'onsgmldeclaration', parser.sgmlDecl) + parser.sgmlDecl = '' + parser.state = S.TEXT + } else if (isQuote(c)) { + parser.state = S.SGML_DECL_QUOTED + parser.sgmlDecl += c + } else { + parser.sgmlDecl += c + } + continue + + case S.SGML_DECL_QUOTED: + if (c === parser.q) { + parser.state = S.SGML_DECL + parser.q = '' + } + parser.sgmlDecl += c + continue + + case S.DOCTYPE: + if (c === '>') { + parser.state = S.TEXT + emitNode(parser, 'ondoctype', parser.doctype) + parser.doctype = true // just remember that we saw it. + } else { + parser.doctype += c + if (c === '[') { + parser.state = S.DOCTYPE_DTD + } else if (isQuote(c)) { + parser.state = S.DOCTYPE_QUOTED + parser.q = c + } + } + continue + + case S.DOCTYPE_QUOTED: + parser.doctype += c + if (c === parser.q) { + parser.q = '' + parser.state = S.DOCTYPE + } + continue + + case S.DOCTYPE_DTD: + parser.doctype += c + if (c === ']') { + parser.state = S.DOCTYPE + } else if (isQuote(c)) { + parser.state = S.DOCTYPE_DTD_QUOTED + parser.q = c + } + continue + + case S.DOCTYPE_DTD_QUOTED: + parser.doctype += c + if (c === parser.q) { + parser.state = S.DOCTYPE_DTD + parser.q = '' + } + continue + + case S.COMMENT: + if (c === '-') { + parser.state = S.COMMENT_ENDING + } else { + parser.comment += c + } + continue + + case S.COMMENT_ENDING: + if (c === '-') { + parser.state = S.COMMENT_ENDED + parser.comment = textopts(parser.opt, parser.comment) + if (parser.comment) { + emitNode(parser, 'oncomment', parser.comment) + } + parser.comment = '' + } else { + parser.comment += '-' + c + parser.state = S.COMMENT + } + continue + + case S.COMMENT_ENDED: + if (c !== '>') { + strictFail(parser, 'Malformed comment') + // allow <!-- blah -- bloo --> in non-strict mode, + // which is a comment of " blah -- bloo " + parser.comment += '--' + c + parser.state = S.COMMENT + } else { + parser.state = S.TEXT + } + continue + + case S.CDATA: + if (c === ']') { + parser.state = S.CDATA_ENDING + } else { + parser.cdata += c + } + continue + + case S.CDATA_ENDING: + if (c === ']') { + parser.state = S.CDATA_ENDING_2 + } else { + parser.cdata += ']' + c + parser.state = S.CDATA + } + continue + + case S.CDATA_ENDING_2: + if (c === '>') { + if (parser.cdata) { + emitNode(parser, 'oncdata', parser.cdata) + } + emitNode(parser, 'onclosecdata') + parser.cdata = '' + parser.state = S.TEXT + } else if (c === ']') { + parser.cdata += ']' + } else { + parser.cdata += ']]' + c + parser.state = S.CDATA + } + continue + + case S.PROC_INST: + if (c === '?') { + parser.state = S.PROC_INST_ENDING + } else if (isWhitespace(c)) { + parser.state = S.PROC_INST_BODY + } else { + parser.procInstName += c + } + continue + + case S.PROC_INST_BODY: + if (!parser.procInstBody && isWhitespace(c)) { + continue + } else if (c === '?') { + parser.state = S.PROC_INST_ENDING + } else { + parser.procInstBody += c + } + continue + + case S.PROC_INST_ENDING: + if (c === '>') { + emitNode(parser, 'onprocessinginstruction', { + name: parser.procInstName, + body: parser.procInstBody + }) + parser.procInstName = parser.procInstBody = '' + parser.state = S.TEXT + } else { + parser.procInstBody += '?' + c + parser.state = S.PROC_INST_BODY + } + continue + + case S.OPEN_TAG: + if (isMatch(nameBody, c)) { + parser.tagName += c + } else { + newTag(parser) + if (c === '>') { + openTag(parser) + } else if (c === '/') { + parser.state = S.OPEN_TAG_SLASH + } else { + if (!isWhitespace(c)) { + strictFail(parser, 'Invalid character in tag name') + } + parser.state = S.ATTRIB + } + } + continue + + case S.OPEN_TAG_SLASH: + if (c === '>') { + openTag(parser, true) + closeTag(parser) + } else { + strictFail(parser, 'Forward-slash in opening tag not followed by >') + parser.state = S.ATTRIB + } + continue + + case S.ATTRIB: + // haven't read the attribute name yet. + if (isWhitespace(c)) { + continue + } else if (c === '>') { + openTag(parser) + } else if (c === '/') { + parser.state = S.OPEN_TAG_SLASH + } else if (isMatch(nameStart, c)) { + parser.attribName = c + parser.attribValue = '' + parser.state = S.ATTRIB_NAME + } else { + strictFail(parser, 'Invalid attribute name') + } + continue + + case S.ATTRIB_NAME: + if (c === '=') { + parser.state = S.ATTRIB_VALUE + } else if (c === '>') { + strictFail(parser, 'Attribute without value') + parser.attribValue = parser.attribName + attrib(parser) + openTag(parser) + } else if (isWhitespace(c)) { + parser.state = S.ATTRIB_NAME_SAW_WHITE + } else if (isMatch(nameBody, c)) { + parser.attribName += c + } else { + strictFail(parser, 'Invalid attribute name') + } + continue + + case S.ATTRIB_NAME_SAW_WHITE: + if (c === '=') { + parser.state = S.ATTRIB_VALUE + } else if (isWhitespace(c)) { + continue + } else { + strictFail(parser, 'Attribute without value') + parser.tag.attributes[parser.attribName] = '' + parser.attribValue = '' + emitNode(parser, 'onattribute', { + name: parser.attribName, + value: '' + }) + parser.attribName = '' + if (c === '>') { + openTag(parser) + } else if (isMatch(nameStart, c)) { + parser.attribName = c + parser.state = S.ATTRIB_NAME + } else { + strictFail(parser, 'Invalid attribute name') + parser.state = S.ATTRIB + } + } + continue + + case S.ATTRIB_VALUE: + if (isWhitespace(c)) { + continue + } else if (isQuote(c)) { + parser.q = c + parser.state = S.ATTRIB_VALUE_QUOTED + } else { + strictFail(parser, 'Unquoted attribute value') + parser.state = S.ATTRIB_VALUE_UNQUOTED + parser.attribValue = c + } + continue + + case S.ATTRIB_VALUE_QUOTED: + if (c !== parser.q) { + if (c === '&') { + parser.state = S.ATTRIB_VALUE_ENTITY_Q + } else { + parser.attribValue += c + } + continue + } + attrib(parser) + parser.q = '' + parser.state = S.ATTRIB_VALUE_CLOSED + continue + + case S.ATTRIB_VALUE_CLOSED: + if (isWhitespace(c)) { + parser.state = S.ATTRIB + } else if (c === '>') { + openTag(parser) + } else if (c === '/') { + parser.state = S.OPEN_TAG_SLASH + } else if (isMatch(nameStart, c)) { + strictFail(parser, 'No whitespace between attributes') + parser.attribName = c + parser.attribValue = '' + parser.state = S.ATTRIB_NAME + } else { + strictFail(parser, 'Invalid attribute name') + } + continue + + case S.ATTRIB_VALUE_UNQUOTED: + if (!isAttribEnd(c)) { + if (c === '&') { + parser.state = S.ATTRIB_VALUE_ENTITY_U + } else { + parser.attribValue += c + } + continue + } + attrib(parser) + if (c === '>') { + openTag(parser) + } else { + parser.state = S.ATTRIB + } + continue + + case S.CLOSE_TAG: + if (!parser.tagName) { + if (isWhitespace(c)) { + continue + } else if (notMatch(nameStart, c)) { + if (parser.script) { + parser.script += '</' + c + parser.state = S.SCRIPT + } else { + strictFail(parser, 'Invalid tagname in closing tag.') + } + } else { + parser.tagName = c + } + } else if (c === '>') { + closeTag(parser) + } else if (isMatch(nameBody, c)) { + parser.tagName += c + } else if (parser.script) { + parser.script += '</' + parser.tagName + parser.tagName = '' + parser.state = S.SCRIPT + } else { + if (!isWhitespace(c)) { + strictFail(parser, 'Invalid tagname in closing tag') + } + parser.state = S.CLOSE_TAG_SAW_WHITE + } + continue + + case S.CLOSE_TAG_SAW_WHITE: + if (isWhitespace(c)) { + continue + } + if (c === '>') { + closeTag(parser) + } else { + strictFail(parser, 'Invalid characters in closing tag') + } + continue + + case S.TEXT_ENTITY: + case S.ATTRIB_VALUE_ENTITY_Q: + case S.ATTRIB_VALUE_ENTITY_U: + var returnState + var buffer + switch (parser.state) { + case S.TEXT_ENTITY: + returnState = S.TEXT + buffer = 'textNode' + break + + case S.ATTRIB_VALUE_ENTITY_Q: + returnState = S.ATTRIB_VALUE_QUOTED + buffer = 'attribValue' + break + + case S.ATTRIB_VALUE_ENTITY_U: + returnState = S.ATTRIB_VALUE_UNQUOTED + buffer = 'attribValue' + break + } + + if (c === ';') { + parser[buffer] += parseEntity(parser) + parser.entity = '' + parser.state = returnState + } else if (isMatch(parser.entity.length ? entityBody : entityStart, c)) { + parser.entity += c + } else { + strictFail(parser, 'Invalid character in entity name') + parser[buffer] += '&' + parser.entity + c + parser.entity = '' + parser.state = returnState + } + + continue + + default: + throw new Error(parser, 'Unknown state: ' + parser.state) + } + } // while + + if (parser.position >= parser.bufferCheckPosition) { + checkBufferLength(parser) + } + return parser + } + + /*! http://mths.be/fromcodepoint v0.1.0 by @mathias */ + /* istanbul ignore next */ + if (!String.fromCodePoint) { + (function () { + var stringFromCharCode = String.fromCharCode + var floor = Math.floor + var fromCodePoint = function () { + var MAX_SIZE = 0x4000 + var codeUnits = [] + var highSurrogate + var lowSurrogate + var index = -1 + var length = arguments.length + if (!length) { + return '' + } + var result = '' + while (++index < length) { + var codePoint = Number(arguments[index]) + if ( + !isFinite(codePoint) || // `NaN`, `+Infinity`, or `-Infinity` + codePoint < 0 || // not a valid Unicode code point + codePoint > 0x10FFFF || // not a valid Unicode code point + floor(codePoint) !== codePoint // not an integer + ) { + throw RangeError('Invalid code point: ' + codePoint) + } + if (codePoint <= 0xFFFF) { // BMP code point + codeUnits.push(codePoint) + } else { // Astral code point; split in surrogate halves + // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae + codePoint -= 0x10000 + highSurrogate = (codePoint >> 10) + 0xD800 + lowSurrogate = (codePoint % 0x400) + 0xDC00 + codeUnits.push(highSurrogate, lowSurrogate) + } + if (index + 1 === length || codeUnits.length > MAX_SIZE) { + result += stringFromCharCode.apply(null, codeUnits) + codeUnits.length = 0 + } + } + return result + } + /* istanbul ignore next */ + if (Object.defineProperty) { + Object.defineProperty(String, 'fromCodePoint', { + value: fromCodePoint, + configurable: true, + writable: true + }) + } else { + String.fromCodePoint = fromCodePoint + } + }()) + } +})(typeof exports === 'undefined' ? this.sax = {} : exports) diff --git a/node_modules/sax/package.json b/node_modules/sax/package.json new file mode 100644 index 0000000..6db58ee --- /dev/null +++ b/node_modules/sax/package.json @@ -0,0 +1,61 @@ +{ + "_from": "sax@^1.2.4", + "_id": "[email protected]", + "_inBundle": false, + "_integrity": "sha512-NqVDv9TpANUjFm0N8uM5GxL36UgKi9/atZw+x7YFnQ8ckwFGKrl4xX4yWtrey3UJm5nP1kUbnYgLopqWNSRhWw==", + "_location": "/sax", + "_phantomChildren": {}, + "_requested": { + "type": "range", + "registry": true, + "raw": "sax@^1.2.4", + "name": "sax", + "escapedName": "sax", + "rawSpec": "^1.2.4", + "saveSpec": null, + "fetchSpec": "^1.2.4" + }, + "_requiredBy": [ + "/needle" + ], + "_resolved": "https://registry.npmjs.org/sax/-/sax-1.2.4.tgz", + "_shasum": "2816234e2378bddc4e5354fab5caa895df7100d9", + "_spec": "sax@^1.2.4", + "_where": "E:\\Documents\\GitHub\\s5nical\\node_modules\\needle", + "author": { + "name": "Isaac Z. Schlueter", + "email": "[email protected]", + "url": "http://blog.izs.me/" + }, + "bugs": { + "url": "https://github.com/isaacs/sax-js/issues" + }, + "bundleDependencies": false, + "deprecated": false, + "description": "An evented streaming XML parser in JavaScript", + "devDependencies": { + "standard": "^8.6.0", + "tap": "^10.5.1" + }, + "files": [ + "lib/sax.js", + "LICENSE", + "README.md" + ], + "homepage": "https://github.com/isaacs/sax-js#readme", + "license": "ISC", + "main": "lib/sax.js", + "name": "sax", + "repository": { + "type": "git", + "url": "git://github.com/isaacs/sax-js.git" + }, + "scripts": { + "postpublish": "git push origin --all; git push origin --tags", + "posttest": "standard -F test/*.js lib/*.js", + "postversion": "npm publish", + "preversion": "npm test", + "test": "tap test/*.js --cov -j4" + }, + "version": "1.2.4" +} |