Merge pull request #108 from remusao/handle-ip

Add ip validation
thom4parisot · Feb 2, 2018 · ac2768d · ac2768d
2 parents 2663273 + 67558dd
commit ac2768d
Show file tree

Hide file tree

Showing 8 changed files with 420 additions and 62 deletions.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 > `tld.js` is a Node.js module written in JavaScript to work against complex domain names, subdomains and well-known TLDs.
 
-It answers with accuracy to questions like _what is `mail.google.com` domain?_,  _what is `a.b.ide.kyoto.jp` subdomain?_ and _is `https://big.data` TLD a well-known one?_.
+It answers with accuracy to questions like _what is `mail.google.com`'s domain?_,  _what is `a.b.ide.kyoto.jp`'s subdomain?_ and _is `https://big.data`'s TLD a well-known one?_.
 
 `tld.js` [runs fast](#performances), is fully tested and is safe to use in the browser (with [browserify][], webpack and others). Because it relies on Mozilla's [public suffix list][], now is a good time to say _thank you_ Mozilla!
 
@@ -43,23 +43,33 @@ This methods returns handy **properties about a URL or a hostname**.
 const tldjs = require('tldjs');
 
 tldjs.parse('https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv');
-// {
-//   "hostname": "spark-public.s3.amazonaws.com",
-//   "isValid": true,
-//   "tldExists": true,
-//   "publicSuffix": "s3.amazonaws.com",
-//   "domain": "spark-public.s3.amazonaws.com",
-//   "subdomain": ""
+// { hostname: 'spark-public.s3.amazonaws.com',
+//   isValid: true,
+//   isIp: false,
+//   tldExists: true,
+//   publicSuffix: 's3.amazonaws.com',
+//   domain: 'spark-public.s3.amazonaws.com',
+//   subdomain: ''
 // }
 
 tldjs.parse('gopher://domain.unknown/');
-// {
-//   "hostname": "domain.unknown",
-//   "isValid": true,
-//   "tldExists": false,
-//   "publicSuffix": "unknown",
-//   "domain": "domain.unknown",
-//   "subdomain": ""
+// { hostname: 'domain.unknown',
+//   isValid: true,
+//   isIp: false,
+//   tldExists: false,
+//   publicSuffix: 'unknown',
+//   domain: 'domain.unknown',
+//   subdomain: ''
+// }
+
+tldjs.parse('https://192.168.0.0')
+// { hostname: '192.168.0.0',
+//   isValid: true,
+//   isIp: true,
+//   tldExists: false,
+//   publicSuffix: null,
+//   domain: null,
+//   subdomain: null
 // }
 ```
 
@@ -154,6 +164,7 @@ isValid('.google.com');     // returns `false`
 isValid('my.fake.domain');  // returns `true`
 isValid('localhost');       // returns `false`
 isValid('https://user:password@example.co.uk:8080/some/path?and&query#hash'); // returns `true`
+isValid('192.168.0.0')      // returns `true`
 ```
 
 # Troubleshooting
@@ -209,23 +220,49 @@ Issues may be awaiting for help so feel free to give a hand, with code or ideas.
 
 # Performances
 
-```
-While interpreting the results, keep in mind that each "op" reported by the benchmark is processing 24 domains
-tldjs#isValid x 230,353 ops/sec ±10.99% (44 runs sampled)
-tldjs#extractHostname x 42,333 ops/sec ±2.82% (85 runs sampled)
-tldjs#tldExists x 15,083 ops/sec ±8.76% (54 runs sampled)
-tldjs#getPublicSuffix x 14,334 ops/sec ±8.00% (80 runs sampled)
-tldjs#getDomain x 15,092 ops/sec ±1.92% (84 runs sampled)
-tldjs#getSubdomain x 13,202 ops/sec ±3.66% (72 runs sampled)
-tldjs#parse x 8,561 ops/sec ±11.78% (55 runs sampled)
-```
+`tld.js` is fast, but keep in mind that it might vary depending on your own
+use-case. Because the library tried to be smart, the speed can be drastically
+different depending on the input (it will be faster if you provide an already
+cleaned hostname, compared to a random URL).
+
+On an Intel i7-6600U (2,60-3,40 GHz):
+
+## For already cleaned hostnames
+
+| Methods           | ops/sec      |
+| ---               | ---          |
+| `isValid`         | ~`8,700,000` |
+| `extractHostname` | ~`8,100,000` |
+| `tldExists`       | ~`2,000,000` |
+| `getPublicSuffix` | ~`1,130,000` |
+| `getDomain`       | ~`1,000,000` |
+| `getSubdomain`    | ~`1,000,000` |
+| `parse`           | ~`850,000`   |
+
+
+## For random URLs
+
+| Methods           | ops/sec       |
+| ---               | ---           |
+| `isValid`         | ~`25,400,000` |
+| `extractHostname` | ~`400,000`    |
+| `tldExists`       | ~`310,000`    |
+| `getPublicSuffix` | ~`240,000`    |
+| `getDomain`       | ~`240,000`    |
+| `getSubdomain`    | ~`240,000`    |
+| `parse`           | ~`230,000`    |
+
 
 You can measure the performance of `tld.js` on your hardware by running the following command:
 
 ```bash
-npx tldjs -c './bin/benchmark.js'
+npm run benchmark
 ```
 
+_Notice_: if this is not fast enough for your use-case, keep in mind that you can
+provide your own `extractHostname` function (which is the bottleneck in
+this benchmark) to `tld.js`.
+
 ## Contributors
 
 This project exists thanks to all the people who contribute. [[Contribute]](CONTRIBUTING.md).
@@ -255,7 +292,6 @@ Support this project by becoming a sponsor. Your logo will show up here with a l
 <a href="https://opencollective.com/tldjs/sponsor/9/website" target="_blank"><img src="https://opencollective.com/tldjs/sponsor/9/avatar.svg"></a>
 
 
-
 # License
 
 [MIT License](LICENSE).

diff --git a/bin/benchmark.js b/bin/benchmark.js
@@ -6,7 +6,7 @@ var tld = require('../index.js');
 var Benchmark = require('benchmark');
 
 
-var DOMAINS = [
+var HOSTNAMES = [
   // No public suffix
   'example.foo.edu.au', // null
   'example.foo.edu.sh', // null
@@ -30,7 +30,10 @@ var DOMAINS = [
   'example.www.ck', // !www.ck
   'foo.bar.baz.city.yokohama.jp', // !city.yokohama.jp
   'example.city.kobe.jp', // !city.kobe.jp
+];
+
 
+var URLS = [
   // IDN labels
   'example.北海道.jp', // 北海道.jp
   'example.和歌山.jp', // 和歌山.jp
@@ -44,54 +47,62 @@ var DOMAINS = [
   'FOO.bar.BAZ.ortsinfo.AT', // null
 
   // Full URLs
-  // '2001:0DB8:0100:F101:0210:A4FF:FEE3:9566',
-  // 'http://user:pass@www.examplegoogle.com:21/blah#baz',
-  // 'http://iris.test.ing/&#x1E0B;&#x0323;/?&#x1E0B;&#x0323;#&#x1E0B;&#x0323;',
-  // 'http://0000000000000300.0xffffffffFFFFFFFF.3022415481470977',
+  '2001:0DB8:0100:F101:0210:A4FF:FEE3:9566',
+  'http://user:pass@www.examplegoogle.com:21/blah#baz',
+  'http://iris.test.ing/&#x1E0B;&#x0323;/?&#x1E0B;&#x0323;#&#x1E0B;&#x0323;',
+  'http://0000000000000300.0xffffffffFFFFFFFF.3022415481470977',
+  'http://192.168.0.1/',
+  'http://%30%78%63%30%2e%30%32%35%30.01%2e',
+  'http://user:pass@[::1]/segment/index.html?query#frag',
+  'https://[::1]',
 ];
 
 
-// TODO - Compare to other libraries
-function main() {
+function bench(values) {
   console.log(
     'While interpreting the results, keep in mind that each "op" reported' +
-    ' by the benchmark is processing ' + DOMAINS.length + ' domains'
+    ' by the benchmark is processing ' + values.length + ' domains'
   );
 
   new Benchmark.Suite()
+    .add('tldjs#isIp', () => {
+      for (var i = 0; i < values.length; i += 1) {
+        tld.isIp(values[i]);
+      }
+    })
     .add('tldjs#isValid', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.isValid(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.isValid(values[i]);
       }
     })
     .add('tldjs#extractHostname', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.extractHostname(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.extractHostname(values[i]);
       }
     })
     .add('tldjs#tldExists', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.tldExists(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.tldExists(values[i]);
       }
     })
     .add('tldjs#getPublicSuffix', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.getPublicSuffix(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.getPublicSuffix(values[i]);
       }
     })
     .add('tldjs#getDomain', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.getDomain(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.getDomain(values[i]);
       }
     })
     .add('tldjs#getSubdomain', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.getSubdomain(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.getSubdomain(values[i]);
       }
     })
     .add('tldjs#parse', () => {
-      for (var i = 0; i < DOMAINS.length; i += 1) {
-        tld.parse(DOMAINS[i]);
+      for (var i = 0; i < values.length; i += 1) {
+        tld.parse(values[i]);
       }
     })
     .on('cycle', function (event) {
@@ -101,4 +112,19 @@ function main() {
 }
 
 
+// TODO - Compare to other libraries
+function main() {
+  console.log('>>> -------------------- <<<');
+  console.log('>>> Only valid hostnames <<<');
+  console.log('>>> -------------------- <<<');
+  bench(HOSTNAMES);
+
+  console.log();
+  console.log('>>> ----------- <<<');
+  console.log('>>> Random URLs <<<');
+  console.log('>>> ----------- <<<');
+  bench(URLS);
+}
+
+
 main();
diff --git a/index.js b/index.js
@@ -1,5 +1,6 @@
 'use strict';
 
+
 // Load rules
 var Trie = require('./lib/suffix-trie.js');
 var allRules = Trie.fromJson(require('./rules.json'));
@@ -10,6 +11,7 @@ var getDomain = require('./lib/domain.js');
 var getPublicSuffix = require('./lib/public-suffix.js');
 var getSubdomain = require('./lib/subdomain.js');
 var isValid = require('./lib/is-valid.js');
+var isIp = require('./lib/is-ip.js');
 var tldExists = require('./lib/tld-exists.js');
 
 
@@ -50,12 +52,26 @@ function factory(options) {
     var result = {
       hostname: _extractHostname(url),
       isValid: null,
-      tldExists: null,
+      isIp: null,
+      tldExists: false,
       publicSuffix: null,
       domain: null,
       subdomain: null,
     };
 
+    if (result.hostname === null) {
+      result.isIp = false;
+      result.isValid = false;
+      return result;
+    }
+
+    // Check if `hostname` is a valid ip address
+    result.isIp = isIp(result.hostname);
+    if (result.isIp) {
+      result.isValid = true;
+      return result;
+    }
+
     // Check if `hostname` is valid
     result.isValid = isValid(result.hostname);
     if (result.isValid === false) return result;