fix: Fixes IRI regex. (#45)

* fix: Fixes IRI regex.

* test(iri): Adds tests for IRIs.

* fix: Moves source map support to dev deps.

Author: ryasmi

.gitignore

@@ -1,6 +1,7 @@
 .DS_STORE
-node_modules
-npm-debug.log
-typings
-coverage
-dist
+/.nyc_output
+/coverage
+/dist
+/node_modules
+/npm-debug.log
+/typings

package-lock.json

@@ -18,7 +18,7 @@
     "commit": "git-cz",
     "build": "tsc",
     "test": "mocha dist/**/*.test.js --exit",
-    "cover": "nyc --lines 95 --check-coverage npm run test",
+    "cover": "nyc --lines 100 --check-coverage npm run test",
     "clean": "rimraf dist",
     "lint": "tslint --project ./tsconfig.json -c ./tslint.json",
     "duplication": "jscpd",
@@ -38,17 +38,19 @@
     "@types/lodash": "4.14.92",
     "@types/mocha": "2.2.46",
     "@types/node": "9.3.0",
+    "@types/source-map-support": "0.4.0",
     "assert": "1.4.1",
     "commitizen": "2.9.6",
     "cz-conventional-changelog": "2.1.0",
     "jscpd": "0.6.17",
     "mocha": "4.1.0",
     "nyc": "11.4.1",
     "rimraf": "2.6.2",
+    "source-map-support": "^0.5.0",
     "tslint": "5.8.0",
     "typescript": "2.6.2"
   },
   "publishConfig": {
     "access": "public"
   }
-}
+}

package.json

@@ -0,0 +1,19 @@
+export const escapedChar = (char: string) => {
+  return `\\${char}`;
+};
+
+export const capturePattern = (pattern: string) => {
+  return `(${pattern})`;
+};
+
+export const delimitedPattern = (pattern: string, delimeter: string) => {
+  return `(?:${pattern})(?:${escapedChar(delimeter)}${pattern})*`;
+};
+
+export const prefixedPattern = (prefix: string, pattern: string) => {
+  return `${escapedChar(prefix)}(${pattern})`;
+};
+
+export const optionalPattern = (pattern: string) => {
+  return `(?:${pattern})?`;
+};

src/helpers/regex.ts

@@ -1,3 +1,6 @@
+import * as sourceMapSupport from 'source-map-support';
+sourceMapSupport.install();
+
 import * as assert from 'assert';
 import validateStatement from './index';
 import { statement } from './tests/factory';

src/index.test.ts

@@ -1,7 +1,28 @@
 /* tslint:disable:max-line-length */
 import { checkRegex, Rule } from 'rulr';
 import { createTypeWarning } from '../warnings/TypeWarning';
+import {
+  escapedChar,
+  optionalPattern,
+  capturePattern,
+  delimitedPattern,
+  prefixedPattern,
+} from '../helpers/regex';
 
-export default checkRegex(
-  /^[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4}:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+[-a-z0-9\._~!\$&\'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=@])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@])|[\uE000-\uF8FF\u0000-\uFFFD|\u0000-\uFFFD\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\xA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u0000-\uFFFD!\$&\'\(\)\*\+,;=:@])|[\/\?])*)?$/i
-, createTypeWarning('Internationalized Resource Identifier (IRI)')) as Rule;
+const normChars = `w_~!$&'()*+,;=:-@`.split('').map(escapedChar).join('');
+const otherChars = '\\u00A0-\\uD7FF\\uF900-\\uFDCF\\uFDF0-\\uFFEF\\uFFEF-\\uFFFD';
+const allChars = `[${normChars}${otherChars}]`;
+const allCharsWithDot = `(?:${allChars}|\\.)`;
+const extChars = `(?:${allChars}|(?:\\%[a-f0-9][a-f0-9]))`;
+
+const scheme = `(?:(\\w+):\\/\\/)`;
+const authority = optionalPattern(capturePattern(delimitedPattern(`${extChars}+`, '.')));
+const path = optionalPattern(prefixedPattern('/', `(?:${allCharsWithDot}+\\/?)*`));
+const query = optionalPattern(prefixedPattern('?', `${extChars}*`));
+const fragment = optionalPattern(prefixedPattern('#', `${extChars}*`));
+
+const regex = new RegExp(`^${scheme}${authority}${path}${query}${fragment}$`, 'i');
+
+const warningConstructor = createTypeWarning('Internationalized Resource Identifier (IRI)');
+
+export default checkRegex(regex, warningConstructor) as Rule;

src/regexValues/iri.ts

@@ -19,4 +19,8 @@ export default (test: Test) => {
   itsValid('ftp://foo.bar/baz', test);
   itsValid('http://⌘➡例子.测试✪उदाहरण.परीकإختبار/䨹', test);
   itsValid('http://-.~_!$&\'()*+,;=:%40:80%2f::::::@example.com', test);
+  itsValid('http://www.example.com/fgdfgd?sdfsdfsdf#fgdgdfg', test);
+
+  // tslint:disable-next-line:max-line-length
+  itsValid('http://some.large.test.string.for.regex/some-large-string/string.html?largeString=largeString&someStrangeText=%D0%9F%D1%81%D0%B5%D0%B2%D0%B4%D0%BE%D1%82%D1%83%D0%B1%D0%B5%D1%80%D0%BA%D1%83%D0%BB%D0%B5%D0%B7', test);
 };

src/tests/regexValues/iri.ts

@@ -8,6 +8,7 @@
     "lib": [
       "es2016"
     ],
+    "sourceMap": true,
     "removeComments": true,
     "preserveConstEnums": true,
     "declaration": true,
@@ -27,4 +28,4 @@
     "dist/**/*"
   ],
   "compileOnSave": true
-}
+}