Merge pull request #231 from remusao/update

feature: add new 'getDomainWithoutSuffix(...)' method

CHANGELOG.md

@@ -4,6 +4,9 @@
 
 *not released*
 
+- Update public suffix ruleset
+- Add new `getDomainWithoutSuffix(...)` method
+
 ### 5.3.2
 
 *2019-07-26*

README.md

@@ -31,6 +31,7 @@ Using the command-line interface:
 $ npx tldts 'http://www.writethedocs.org/conf/eu/2017/'
 {
   "domain": "writethedocs.org",
+  "domainWithoutSuffix": "writethedocs",
   "hostname": "www.writethedocs.org",
   "isIcann": true,
   "isIp": false,
@@ -47,6 +48,7 @@ const { parse } = require('tldts');
 // Retrieving hostname related informations of a given URL
 parse('http://www.writethedocs.org/conf/eu/2017/');
 // { domain: 'writethedocs.org',
+//   domainWithoutSuffix: 'writethedocs',
 //   hostname: 'www.writethedocs.org',
 //   isIcann: true,
 //   isIp: false,

packages/tldts-core/src/domain-without-suffix.ts

@@ -0,0 +1,12 @@
+
+/**
+ * Return the part of domain without suffix.
+ *
+ * Example: for domain 'foo.com', the result would be 'foo'.
+ */
+export default function getDomainWithoutSuffix(domain: string, suffix: string): string {
+  // Note: here `domain` and `suffix` cannot have the same length because in
+  // this case we set `domain` to `null` instead. It is thus safe to assume
+  // that `suffix` is shorter than `domain`.
+  return domain.slice(0, -suffix.length - 1);
+}

packages/tldts-core/src/factory.ts

@@ -5,6 +5,7 @@
  */
 
 import getDomain from './domain';
+import getDomainWithoutSuffix from './domain-without-suffix';
 import extractHostname from './extract-hostname';
 import isIp from './is-ip';
 import isValidHostname from './is-valid';
@@ -26,6 +27,7 @@ export interface IResult {
   subdomain: string | null;
   domain: string | null;
   publicSuffix: string | null;
+  domainWithoutSuffix: string | null;
 
   // Specifies if `publicSuffix` comes from the ICANN or PRIVATE section of the list
   isIcann: boolean | null;
@@ -58,6 +60,7 @@ export function parseImpl(
   const options: IOptions = setDefaults(partialOptions);
   const result: IResult = {
     domain: null,
+    domainWithoutSuffix: null,
     hostname: null,
     isIcann: null,
     isIp: null,
@@ -128,6 +131,15 @@ export function parseImpl(
 
   // Extract subdomain
   result.subdomain = getSubdomain(result.hostname, result.domain);
+  if (step === FLAG.SUB_DOMAIN) {
+    return result;
+  }
+
+  // Extract domain without suffix
+  result.domainWithoutSuffix = getDomainWithoutSuffix(
+    result.domain,
+    result.publicSuffix,
+  );
 
   return result;
 }

packages/tldts-experimental/index.ts

@@ -32,3 +32,10 @@ export function getHostname(
 ): string | null {
   return parseImpl(url, FLAG.HOSTNAME, suffixLookup, options).hostname;
 }
+
+export function getDomainWithoutSuffix(
+  url: string,
+  options?: Partial<IOptions>,
+): string | null {
+  return parseImpl(url, FLAG.ALL, suffixLookup, options).domainWithoutSuffix;
+}

packages/tldts-tests/src/tldts-tests.ts

@@ -553,6 +553,20 @@ export default function test(tldts: any): void {
     });
   });
 
+  describe('getDomainWithoutSuffix method', () => {
+    it('should return null if the domain cannot be found', () => {
+      expect(tldts.getDomainWithoutSuffix('not-a-validHost')).toEqual(null);
+    });
+
+    it('should return null if domain and suffix are the same', () => {
+      expect(tldts.getDomainWithoutSuffix('co.uk')).toEqual(null);
+    });
+
+    it('should return domain without suffix if domain exists', () => {
+      expect(tldts.getDomainWithoutSuffix('https://sub.foo.co.uk')).toEqual('foo');
+    });
+  });
+
   describe('getSubdomain method', () => {
     it('should return null if the domain cannot be found', () => {
       expect(tldts.getSubdomain('not-a-validHost')).toEqual(null);
@@ -637,6 +651,7 @@ export default function test(tldts: any): void {
     const mockResponse = (hostname: string) => {
       return {
         domain: null,
+        domainWithoutSuffix: null,
         hostname,
         isIcann: null,
         isIp: true,
@@ -649,6 +664,7 @@ export default function test(tldts: any): void {
     it('fallback to wildcard', () => {
       expect(tldts.parse('https://foo.bar.badasdasdada')).toEqual({
         domain: 'bar.badasdasdada',
+        domainWithoutSuffix: 'bar',
         hostname: 'foo.bar.badasdasdada',
         isIcann: false,
         isIp: false,
@@ -683,6 +699,7 @@ export default function test(tldts: any): void {
     it('disable ip detection', () => {
       expect(tldts.parse('http://192.168.0.1/', { detectIp: false })).toEqual({
         domain: '0.1',
+        domainWithoutSuffix: '0',
         hostname: '192.168.0.1',
         isIcann: false,
         isIp: null,

packages/tldts/README.md

@@ -26,6 +26,7 @@ Using the command-line interface:
 $ npx tldts 'http://www.writethedocs.org/conf/eu/2017/'
 {
   "domain": "writethedocs.org",
+  "domainWithoutSuffix": "writethedocs",
   "hostname": "www.writethedocs.org",
   "isIcann": true,
   "isIp": false,
@@ -42,6 +43,7 @@ const { parse } = require('tldts');
 // Retrieving hostname related informations of a given URL
 parse('http://www.writethedocs.org/conf/eu/2017/');
 // { domain: 'writethedocs.org',
+//   domainWithoutSuffix: 'writethedocs',
 //   hostname: 'www.writethedocs.org',
 //   isIcann: true,
 //   isIp: false,
@@ -65,6 +67,7 @@ Alternatively, you can try it *directly in your browser* here: https://npm.runki
 * `tldts.getDomain(url | hostname, options)`
 * `tldts.getPublicSuffix(url | hostname, options)`
 * `tldts.getSubdomain(url, | hostname, options)`
+* `tldts.getDomainWithoutSuffix(url | hostname, options)`
 
 The behavior of `tldts` can be customized using an `options` argument for all
 the functions exposed as part of the public API. This is useful to both change
@@ -103,6 +106,7 @@ const tldts = require('tldts');
 
 tldts.parse('https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv');
 // { domain: 'amazonaws.com',
+//   domainWithoutSuffix: 'amazonaws',
 //   hostname: 'spark-public.s3.amazonaws.com',
 //   isIcann: true,
 //   isIp: false,
@@ -112,6 +116,7 @@ tldts.parse('https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv');
 
 tldts.parse('https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv', { allowPrivateDomains: true })
 // { domain: 'spark-public.s3.amazonaws.com',
+//   domainWithoutSuffix: 'spark-public',
 //   hostname: 'spark-public.s3.amazonaws.com',
 //   isIcann: false,
 //   isIp: false,
@@ -121,6 +126,7 @@ tldts.parse('https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv',
 
 tldts.parse('gopher://domain.unknown/');
 // { domain: 'domain.unknown',
+//   domainWithoutSuffix: 'domain',
 //   hostname: 'domain.unknown',
 //   isIcann: false,
 //   isIp: false,
@@ -130,6 +136,7 @@ tldts.parse('gopher://domain.unknown/');
 
 tldts.parse('https://192.168.0.0') // IPv4
 // { domain: null,
+//   domainWithoutSuffix: null,
 //   hostname: '192.168.0.0',
 //   isIcann: null,
 //   isIp: true,
@@ -139,6 +146,7 @@ tldts.parse('https://192.168.0.0') // IPv4
 
 tldts.parse('https://[::1]') // IPv6
 // { domain: null,
+//   domainWithoutSuffix: null,
 //   hostname: '::1',
 //   isIcann: null,
 //   isIp: true,
@@ -148,6 +156,7 @@ tldts.parse('https://[::1]') // IPv6
 
 tldts.parse('[email protected]') // email
 // { domain: 'emailprovider.co.uk',
+//   domainWithoutSuffix: 'emailprovider',
 //   hostname: 'emailprovider.co.uk',
 //   isIcann: true,
 //   isIp: false,
@@ -156,15 +165,16 @@ tldts.parse('[email protected]') // email
 //   subdomain: '' }
 ```
 
-| Property Name  | Type   | Description                                 |
-|:-------------- |:------ |:------------------------------------------- |
-| `hostname`     | `str`  | `hostname` of the input extracted automatically |
-| `domain`       | `str`  | Domain (tld + sld)                          |
-| `subdomain`    | `str`  | Sub domain (what comes after `domain`)      |
-| `publicSuffix` | `str`  | Public Suffix (tld) of `hostname`           |
-| `isIcann`      | `bool` | Does TLD come from ICANN part of the list   |
-| `isPrivate`    | `bool` | Does TLD come from Private part of the list |
-| `isIP`         | `bool` | Is `hostname` an IP address?                |
+| Property Name         | Type   | Description                                     |
+|:--------------------- |:------ |:----------------------------------------------- |
+| `hostname`            | `str`  | `hostname` of the input extracted automatically |
+| `domain`              | `str`  | Domain (tld + sld)                              |
+| `domainWithoutSuffix` | `str`  | Domain without public suffix                    |
+| `subdomain`           | `str`  | Sub domain (what comes after `domain`)          |
+| `publicSuffix`        | `str`  | Public Suffix (tld) of `hostname`               |
+| `isIcann`             | `bool` | Does TLD come from ICANN part of the list       |
+| `isPrivate`           | `bool` | Does TLD come from Private part of the list     |
+| `isIP`                | `bool` | Is `hostname` an IP address?                    |
 
 
 ## Single purpose methods
@@ -204,6 +214,22 @@ getDomain('fr.t.co');           // returns `t.co`
 getDomain('https://user:[email protected]:8080/some/path?and&query#hash'); // returns `example.co.uk`
 ```
 
+### getDomainWithoutSuffix(url | hostname, options?)
+
+Returns the domain (as returned by `getDomain(...)`) without the public suffix part.
+
+```javascript
+const { getDomainWithoutSuffix } = require('tldts');
+
+getDomainWithoutSuffix('google.com');        // returns `google`
+getDomainWithoutSuffix('fr.google.com');     // returns `google`
+getDomainWithoutSuffix('fr.google.google');  // returns `google`
+getDomainWithoutSuffix('foo.google.co.uk');  // returns `google`
+getDomainWithoutSuffix('t.co');              // returns `t`
+getDomainWithoutSuffix('fr.t.co');           // returns `t`
+getDomainWithoutSuffix('https://user:[email protected]:8080/some/path?and&query#hash'); // returns `example`
+```
+
 ### getSubdomain(url | hostname, options?)
 
 Returns the complete subdomain for a given string.

packages/tldts/index.ts

@@ -32,3 +32,10 @@ export function getHostname(
 ): string | null {
   return parseImpl(url, FLAG.HOSTNAME, suffixLookup, options).hostname;
 }
+
+export function getDomainWithoutSuffix(
+  url: string,
+  options?: Partial<IOptions>,
+): string | null {
+  return parseImpl(url, FLAG.ALL, suffixLookup, options).domainWithoutSuffix;
+}