parse-domain 0.1.1 → 0.2.2

package/.jshintignore

@@ -1 +1,18 @@
-node_modules
+lib-cov
+*.seed
+*.log
+*.csv
+*.dat
+*.out
+*.pid
+*.gz
+
+pids
+logs
+results
+
+npm-debug.log
+node_modules
+coverage
+examples
+.idea

package/.jshintrc

@@ -1,48 +1,48 @@
-{
-    "browser": false,
-    "node": true,
-    "expr": true,
-    "predef": [         // Extra globals.
-        "describe",
-        "it",
-        "before",
-        "after",
-        "beforeEach",
-        "afterEach"
-    ],
-
-    "curly": true,     // Require {} for every new block or scope.
-    "eqeqeq": true,     // Require triple equals i.e. `===`.
-    "forin": true,     // Tolerate `for in` loops without `hasOwnPrototype`.
-    "immed": true,     // Require immediate invocations to be wrapped in parens e.g. `( function(){}() );`
-    "latedef": false,     // Prohibit variable use before definition.
-    "newcap": false,     // Require capitalization of all constructor functions e.g. `new F()`.
-    "noempty": true,     // Prohibit use of empty blocks.
-    "nonew": false,     // Prohibit use of constructors for side-effects.
-    "plusplus": false,     // Prohibit use of `++` & `--`.
-    "undef": true,     // Require all non-global variables be declared before they are used.
-    "strict": true,     // Require `use strict` pragma in every file.
-    "trailing": true,    // Prohibit trailing whitespaces.
-
-    "asi": false,    // Tolerate Automatic Semicolon Insertion (no semicolons).
-    "boss": false,    // Tolerate assignments inside if, for & while. Usually conditions & loops are for comparison, not assignments.
-    "debug": false,    // Allow debugger statements e.g. browser breakpoints.
-    "eqnull": false,    // Tolerate use of `== null`.
-    "esnext": false,    // Allow ES.next specific features such as `const` and `let`.
-    "evil": false,    // Tolerate use of `eval`.
-    "funcscope": false,    // Tolerate declarations of variables inside of control structures while accessing them later from the outside.
-    "globalstrict": false,    // Allow global "use strict" (also enables 'strict').
-    "iterator": false,    // Allow usage of __iterator__ property.
-    "lastsemic": false,    // Tolerat missing semicolons when the it is omitted for the last statement in a one-line block.
-    "laxbreak": false,    // Tolerate unsafe line breaks e.g. `return [\n] x` without semicolons.
-    "laxcomma": false,    // Suppress warnings about comma-first coding style.
-    "loopfunc": false,    // Allow functions to be defined within loops.
-    "multistr": false,    // Tolerate multi-line strings.
-    "proto": false,    // Tolerate __proto__ property. This property is deprecated.
-    "scripturl": false,    // Tolerate script-targeted URLs.
-    "smarttabs": false,    // Tolerate mixed tabs and spaces when the latter are used for alignmnent only.
-    "shadow": false,    // Allows re-define variables later in code e.g. `var x=1; x=2;`.
-    "sub": true,    // Tolerate all forms of subscript notation besides dot notation e.g. `dict['key']` instead of `dict.key`.
-    "supernew": false,    // Tolerate `new function () { ... };` and `new Object;`.
-    "validthis": false    // Tolerate strict violations when the code is running in strict mode and you use this in a non-constructor function
+{
+    "browser": false,
+    "node": true,
+    "expr": true,
+    "predef": [         // Extra globals.
+        "describe",
+        "it",
+        "before",
+        "after",
+        "beforeEach",
+        "afterEach"
+    ],
+
+    "curly": true,     // Require {} for every new block or scope.
+    "eqeqeq": true,     // Require triple equals i.e. `===`.
+    "forin": true,     // Tolerate `for in` loops without `hasOwnPrototype`.
+    "immed": true,     // Require immediate invocations to be wrapped in parens e.g. `( function(){}() );`
+    "latedef": false,     // Prohibit variable use before definition.
+    "newcap": false,     // Require capitalization of all constructor functions e.g. `new F()`.
+    "noempty": true,     // Prohibit use of empty blocks.
+    "nonew": false,     // Prohibit use of constructors for side-effects.
+    "plusplus": false,     // Prohibit use of `++` & `--`.
+    "undef": true,     // Require all non-global variables be declared before they are used.
+    "strict": true,     // Require `use strict` pragma in every file.
+    "trailing": true,    // Prohibit trailing whitespaces.
+
+    "asi": false,    // Tolerate Automatic Semicolon Insertion (no semicolons).
+    "boss": false,    // Tolerate assignments inside if, for & while. Usually conditions & loops are for comparison, not assignments.
+    "debug": false,    // Allow debugger statements e.g. browser breakpoints.
+    "eqnull": false,    // Tolerate use of `== null`.
+    "esnext": false,    // Allow ES.next specific features such as `const` and `let`.
+    "evil": false,    // Tolerate use of `eval`.
+    "funcscope": false,    // Tolerate declarations of variables inside of control structures while accessing them later from the outside.
+    "globalstrict": false,    // Allow global "use strict" (also enables 'strict').
+    "iterator": false,    // Allow usage of __iterator__ property.
+    "lastsemic": false,    // Tolerat missing semicolons when the it is omitted for the last statement in a one-line block.
+    "laxbreak": false,    // Tolerate unsafe line breaks e.g. `return [\n] x` without semicolons.
+    "laxcomma": false,    // Suppress warnings about comma-first coding style.
+    "loopfunc": false,    // Allow functions to be defined within loops.
+    "multistr": false,    // Tolerate multi-line strings.
+    "proto": false,    // Tolerate __proto__ property. This property is deprecated.
+    "scripturl": false,    // Tolerate script-targeted URLs.
+    "smarttabs": false,    // Tolerate mixed tabs and spaces when the latter are used for alignmnent only.
+    "shadow": false,    // Allows re-define variables later in code e.g. `var x=1; x=2;`.
+    "sub": true,    // Tolerate all forms of subscript notation besides dot notation e.g. `dict['key']` instead of `dict.key`.
+    "supernew": false,    // Tolerate `new function () { ... };` and `new Object;`.
+    "validthis": false    // Tolerate strict violations when the code is running in strict mode and you use this in a non-constructor function
 }

package/.npmignore

@@ -1,17 +1,20 @@
-lib-cov
-*.seed
-*.log
-*.csv
-*.dat
-*.out
-*.pid
-*.gz
-
-pids
-logs
-results
-
-examples
-node_modules
-npm-debug.log
-.idea
+lib-cov
+*.seed
+*.log
+*.csv
+*.dat
+*.out
+*.pid
+*.gz
+
+pids
+logs
+results
+
+npm-debug.log
+node_modules
+coverage
+examples
+test
+assets
+.idea

package/.travis.yml

@@ -1,7 +1,11 @@
-language: node_js
-node_js:
-  - "0.10"
-  - "0.11"
-
-script:
-  - npm test
+language: node_js
+node_js:
+  - "0.10"
+  - "0.11"
+
+script:
+  - npm test
+after_success:
+  - npm install -g istanbul
+  - npm install coveralls
+  - istanbul cover ./node_modules/mocha/bin/_mocha --report lcovonly -- -R spec && cat ./coverage/lcov.info | ./node_modules/coveralls/bin/coveralls.js && rm -rf ./coverage

package/LICENSE

@@ -1,24 +1,24 @@
-This is free and unencumbered software released into the public domain.
-
-Anyone is free to copy, modify, publish, use, compile, sell, or
-distribute this software, either in source code form or as a compiled
-binary, for any purpose, commercial or non-commercial, and by any
-means.
-
-In jurisdictions that recognize copyright laws, the author or authors
-of this software dedicate any and all copyright interest in the
-software to the public domain. We make this dedication for the benefit
-of the public at large and to the detriment of our heirs and
-successors. We intend this dedication to be an overt act of
-relinquishment in perpetuity of all present and future rights to this
-software under copyright law.
-
-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 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.
-
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+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 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.
+
 For more information, please refer to <http://unlicense.org>

package/README.md

@@ -1,65 +1,137 @@
-parse-domain
-========================================================================
-**Splits an url into sub-domain, domain and top-level-domain.**
-
-Since domains are handled differently across different countries and organizations, splitting an url into sub-domain, domain and top-level-domain is not a simple regexp. **parse-domain** uses a [large list of known tlds](https://github.com/peerigon/parse-domain/blob/master/lib/build/tld.txt) (borrowed from [http://publicsuffix.org](http://publicsuffix.org/list/effective_tld_names.dat)) to recognize different parts of the domain.
-
-```javascript
-var parseDomain = require("parse-domain");
-
-expect(parseDomain("some.subdomain.example.co.uk")).to.eql({
-    subdomain: "some.subdomain",
-    domain: "example",
-    tld: "co.uk"
-});
-
-expect(parseDomain("https://user:password@example.co.uk:8080/some/path?and&query#hash")).to.eql({
-    subdomain: "",
-    domain: "example",
-    tld: "co.uk"
-});
-
-expect(parseDomain("unknown.tld.kk")).to.equal(null);
-expect(parseDomain("invalid url")).to.equal(null);
-expect(parseDomain({})).to.equal(null);
-```
-
-<br />
-
-Setup
-------------------------------------------------------------------------
-
-[![npm status](https://nodei.co/npm/parse-domain.png?downloads=true&stars=true)](https://npmjs.org/package/parse-domain)
-
-[![build status](https://travis-ci.org/peerigon/parse-domain.png)](http://travis-ci.org/peerigon/parse-domain)
-[![dependencies](https://david-dm.org/peerigon/parse-domain.png)](http://david-dm.org/peerigon/parse-domain)
-[![devDependencies](https://david-dm.org/peerigon/parse-domain/dev-status.png)](http://david-dm.org/peerigon/parse-domain#info=devDependencies)
-
-[![browser support](https://ci.testling.com/peerigon/parse-domain.png)
-](https://ci.testling.com/peerigon/parse-domain)
-
-<br />
-
-API
-------------------------------------------------------------------------
-
-### parseDomain(url: String): ParsedDomain|null
-
-Returns `null` if `url` has an unknown tld or if it's not a valid url.
-
-### ParsedDomain
-
-```
-{
-    tld: String,
-    domain: String,
-    subdomain: String
-}
-```
-
-<br />
-
-License
-------------------------------------------------------------------------
-
-Unlicense
+parse-domain
+============
+**Splits a URL into sub-domain, domain and the effective top-level domain.**
+
+[![](https://img.shields.io/npm/v/parse-domain.svg)](https://www.npmjs.com/package/parse-domain)
+[![](https://img.shields.io/npm/dm/parse-domain.svg)](https://www.npmjs.com/package/parse-domain)
+[![Dependency Status](https://david-dm.org/peerigon/parse-domain.svg)](https://david-dm.org/peerigon/parse-domain)
+
+Since domains are handled differently across different countries and organizations, splitting a URL into sub-domain, domain and top-level-domain parts is not a simple regexp. **parse-domain** uses a [large list of effective tld names](http://publicsuffix.org/list/effective_tld_names.dat) from publicsuffix.org to recognize different parts of the domain.
+
+Please also read the note on [effective top-level domains](#note-on-effective-top-level-domains).
+
+<br />
+
+Installation
+------------------------------------------------------------------------
+
+```sh
+npm install --save parse-domain
+```
+
+<br />
+
+Usage
+------------------------------------------------------------------------
+
+```javascript
+// long subdomains can be handled
+expect(parseDomain("some.subdomain.example.co.uk")).to.eql({
+    subdomain: "some.subdomain",
+    domain: "example",
+    tld: "co.uk"
+});
+
+// usernames, passwords and ports are disregarded
+expect(parseDomain("https://user:password@example.co.uk:8080/some/path?and&query#hash")).to.eql({
+    subdomain: "",
+    domain: "example",
+    tld: "co.uk"
+});
+
+// non-canonical top-level domains are ignored
+expect(parseDomain("unknown.tld.kk")).to.equal(null);
+
+// invalid urls are also ignored
+expect(parseDomain("invalid url")).to.equal(null);
+expect(parseDomain({})).to.equal(null);
+```
+
+### Introducing custom tlds
+
+```javascript
+// custom top-level domains can optionally be specified
+expect(parseDomain("mymachine.local",{ customTlds: ["local"] })).to.eql({
+    subdomain: "",
+    domain: "mymachine",
+    tld: "local"
+});
+
+// custom regexps can optionally be specified (instead of customTlds)
+expect(parseDomain("localhost",{ customTlds:/localhost|\.local/ })).to.eql({
+    subdomain: "",
+    domain: "",
+    tld: "localhost"
+});
+```
+
+It can sometimes be helpful to apply the customTlds argument using a helper function
+
+```javascript
+function parseLocalDomains(url) {
+    var options = {
+        customTlds: /localhost|\.local/
+    };
+    return parseDomain(url, options);
+}
+
+expect(parseLocalDomains("localhost")).to.eql({
+    subdomain: "",
+    domain: "",
+    tld: "localhost"
+});
+expect(parseLocalDomains("mymachine.local")).to.eql({
+    subdomain: "",
+    domain: "mymachine",
+    tld: "local"
+});
+```
+
+<br />
+
+API
+------------------------------------------------------------------------
+
+### `parseDomain(url: String, options: ParseOptions): ParsedDomain|null`
+
+Returns `null` if `url` has an unknown tld or if it's not a valid url.
+
+#### `ParseOptions`
+```javascript
+{
+    customTlds: RegExp|String[]
+}
+```
+
+#### `ParsedDomain`
+```javascript
+{
+    tld: String,
+    domain: String,
+    subdomain: String
+}
+```
+
+<br />
+
+Note on effective top-level domains
+------------------------------------------------------------------------
+
+Technically, the top-level domain is *always* the part after the last dot. That's why publicsuffix.org is a list of *effective* top-level domains: It lists all top-level domains where users are allowed to host any content. That's why `foo.blogspot.com` will be split into
+
+```javascript
+{
+    tld: "blogspot.com",
+    domain: "foo",
+    subdomain: ""
+}
+```
+
+See also [#4](https://github.com/peerigon/parse-domain/issues/4)
+
+<br />
+
+License
+------------------------------------------------------------------------
+
+Unlicense

package/lib/build/buildRegex.js

@@ -1,18 +1,34 @@
-"use strict";
-
-var fs = require("fs"),
-    path = require("path");
-
-var tld,
-    src;
-
-tld = fs.readFileSync(__dirname + "/tld.txt", "utf8")
-    .replace(/(\/\/.+)\r?\n/gi, "")
-    .replace(/[\r?\n]+/g, "|")
-    .replace(/\./g, "\\.")
-    .replace(/\*/g, "[^\\.]*")
-    .slice(1, -1);
-
-src = "module.exports = /.(" + tld + ")$/;";
-
-fs.writeFileSync(path.resolve(__dirname, "../tld.js"), src, "utf8");
+"use strict";
+
+var fs = require("fs"),
+    path = require("path");
+
+var txtPath = path.resolve(__dirname, "./tld.txt"),
+    regexPath = path.resolve(__dirname, "../tld.js"),
+    tld,
+    src;
+
+console.log("Reading " + txtPath + " ...");
+
+tld = fs.readFileSync(txtPath, "utf8")
+    .replace(/(\/\/.+)\r?\n/gi, "")
+    .replace(/[\r?\n]+/g, "|")
+    .replace(/\./g, "\\.")
+    .replace(/\*/g, "[^.]+")
+    .slice(1, -1);
+
+src = "module.exports = /\\.(" + tld + ")$/;";
+
+console.log("Writing module at " + regexPath + " ...");
+
+fs.writeFileSync(regexPath, src, "utf8");
+
+console.log("Checking if it's valid JavaScript ...");
+
+var regex = require(regexPath);
+
+if (regex instanceof RegExp === false) {
+    throw new Error("Generated regex is not instanceof RegExp. Instead saw " + regex);
+}
+
+console.log("Regex is ok, exiting now");