posthtml-parser
Advanced tools
Comparing version 0.1.3 to 0.2.0
58
index.js
@@ -1,10 +0,18 @@ | ||
/*jshint -W082 */ | ||
'use strict'; | ||
var htmlparser = require('htmlparser2'); | ||
var isObject = require('isobject'); | ||
/** | ||
* @see https://github.com/fb55/htmlparser2/wiki/Parser-options | ||
*/ | ||
var defaultOptions = {lowerCaseTags: false}; | ||
/** | ||
* Parse html to PostHTMLTree | ||
* @param {String} html | ||
* @return {Object} | ||
* @param {Object} [options=defaultOptions] | ||
* @return {PostHTMLTree} | ||
*/ | ||
module.exports = function postHTMLParser(html) { | ||
function postHTMLParser(html, options) { | ||
var bufArray = [], | ||
@@ -19,3 +27,5 @@ results = []; | ||
onprocessinginstruction: function(name, data) { | ||
name.toLowerCase() === '!doctype' && results.push('<' + data + '>'); | ||
if (name.toLowerCase() === '!doctype') { | ||
results.push('<' + data + '>'); | ||
} | ||
}, | ||
@@ -35,8 +45,8 @@ oncomment: function(data) { | ||
onopentag: function(tag, attrs) { | ||
var buf = {}; | ||
var buf = { tag: tag }; | ||
buf.tag = tag; | ||
if (Object.keys(attrs).length) { | ||
buf.attrs = attrs; | ||
} | ||
if (!isEmpty(attrs)) buf.attrs = attrs; | ||
bufArray.push(buf); | ||
@@ -47,3 +57,3 @@ }, | ||
if (bufArray.length === 0) { | ||
if (!bufArray.length) { | ||
results.push(buf); | ||
@@ -54,5 +64,6 @@ return; | ||
var last = bufArray.last(); | ||
if (!(last.content instanceof Array)) { | ||
if (!Array.isArray(last.content)) { | ||
last.content = []; | ||
} | ||
last.content.push(buf); | ||
@@ -70,3 +81,3 @@ }, | ||
} | ||
}, {lowerCaseTags: false}); | ||
}, options || defaultOptions); | ||
@@ -77,11 +88,22 @@ parser.write(html); | ||
return results; | ||
}; | ||
} | ||
function isEmpty(obj) { | ||
for (var key in obj) { | ||
if (Object.prototype.hasOwnProperty.call(obj, key)) { | ||
return false; | ||
} | ||
function parserWrapper() { | ||
var option; | ||
function parser(html) { | ||
var opt = option || defaultOptions; | ||
return postHTMLParser(html, opt); | ||
} | ||
return true; | ||
if (arguments.length === 1 && isObject(arguments[0])) { | ||
option = arguments[0]; | ||
return parser; | ||
} | ||
option = arguments[1]; | ||
return parser(arguments[0]); | ||
} | ||
module.exports = parserWrapper; | ||
module.exports.defaultOptions = defaultOptions; |
{ | ||
"name": "posthtml-parser", | ||
"version": "0.1.3", | ||
"version": "0.2.0", | ||
"description": "Parse HTML/XML to PostHTMLTree", | ||
@@ -20,6 +20,3 @@ "keywords": [ | ||
}, | ||
"repository": { | ||
"type": "git", | ||
"url": "git+https://github.com/posthtml/posthtml-parser.git" | ||
}, | ||
"repository": "posthtml/posthtml-parser", | ||
"author": "Ivan Voischev <voischev.ivan@ya.ru>", | ||
@@ -32,3 +29,4 @@ "license": "MIT", | ||
"dependencies": { | ||
"htmlparser2": "^3.8.3" | ||
"htmlparser2": "^3.8.3", | ||
"isobject": "^2.1.0" | ||
}, | ||
@@ -40,4 +38,7 @@ "devDependencies": { | ||
"jshint": "^2.8.0", | ||
"mocha": "^2.3.3" | ||
"mocha": "^2.3.3", | ||
"rewire": "^2.5.2", | ||
"sinon": "^1.17.4", | ||
"sinon-chai": "^2.8.0" | ||
} | ||
} |
@@ -6,3 +6,3 @@ # posthtml-parser | ||
Parse HTML/XML to [PostHTMLTree](https://github.com/posthtml/posthtml#posthtml-json-tree-example). | ||
Parse HTML/XML to [PostHTML AST](https://github.com/posthtml/posthtml-parser#posthtml-ast-format). | ||
More about [PostHTML](https://github.com/posthtml/posthtml#readme) | ||
@@ -17,5 +17,5 @@ | ||
## Usage | ||
## Usage | ||
#### input HTML | ||
#### Input HTML | ||
```html | ||
@@ -27,7 +27,7 @@ <a class="animals" href="#"> | ||
```js | ||
var parser = require('posthtml-parser'); | ||
var fs = require('fs'); | ||
var html = fs.readFileSync('path/to/input.html').toString(); | ||
const parser = require('posthtml-parser') | ||
const fs = require('fs') | ||
const html = fs.readFileSync('path/to/input.html').toString() | ||
clonsole.log(parser(html)); // Look #Result PostHTMLTree | ||
console.log(parser(html)) // Logs a PostHTML AST | ||
``` | ||
@@ -65,4 +65,22 @@ | ||
## PostHTML AST Format | ||
Any parser being used with PostHTML should return a standard PostHTML [Abstract Syntax Tree](https://www.wikiwand.com/en/Abstract_syntax_tree) (AST). Fortunately, this is a very easy format to produce and understand. The AST is an array that can contain strings and objects. Any strings represent plain text content to be written to the output. Any objects represent HTML tags. | ||
Tag objects generally look something like this: | ||
```js | ||
{ | ||
tag: 'div', | ||
attrs: { | ||
class: 'foo' | ||
}, | ||
content: ['hello world!'] | ||
} | ||
``` | ||
Tag objects can contain three keys. The `tag` key takes the name of the tag as the value. This can include custom tags. The optional `attrs` key takes an object with key/value pairs representing the attributes of the html tag. A boolean attribute has an empty string as its value. Finally, the optional `content` key takes an array as its value, which is a PostHTML AST. In this manner, the AST is a tree that should be walked recursively. | ||
## License | ||
[MIT](LICENSE) |
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
No repository
Supply chain riskPackage does not have a linked source code repository. Without this field, a package will have no reference to the location of the source code use to generate the package.
Found 1 instance in 1 package
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
7587
7
83
83
2
8
1
+ Addedisobject@^2.1.0
+ Addedisarray@1.0.0(transitive)
+ Addedisobject@2.1.0(transitive)