release for v0.0.2

README.md

@@ -85,7 +85,7 @@ The crawler will then generate the results based on the links found **within the
 **Required inputs**
 - URL linking to the sitemap file
 - Examples of valid sitemap format
-  - XML (Recommended): https://www.sitemaps.org/sitemap.xml  
+  - XML (Recommended): https://www.sitemaps.org/sitemap.xml
   - RSS: https://itunes.apple.com/gb/rss/customerreviews/id=317212648/xml
   - Text: https://www.xml-sitemaps.com/urllist.txt  
 - For more information on sitemap: https://www.sitemaps.org/protocol.html
@@ -140,4 +140,53 @@ Scanning website...
 #Console results
 
 user@user-MacBook-Pro purple-hats %
-```
+```
+
+### 3. Crawling login page
+The crawler will automated the login and recursively visit the links to generate the results from **all the pages found from the input domain**.
+
+**Required inputs**
+- A website URL
+- User's login credential
+- Selectors of the username field, password field and submit button field
+
+**Sample Output - Public Domain with Login Page**
+```console
+user@user-MacBook-Pro  Desktop % cd purple-hats
+user@user-MacBook-Pro purple-hats %  bash run.sh
+Welcome to HAT's Accessibility Testing Tool!
+We recommend using Chrome browser for the best experience.
+
+What would you like to scan today?
+1) sitemap.xml file containing links
+2) public domain URL
+#? 2
+Please enter domain URL: https://fontawesome.com/sessions/sign-in
+Do you need to login to your domain? Y/N: y
+Please enter your login ID: [email protected]
+Please enter your password: 
+
+Now, go to your browser and right-click on these 3 elements,
+1. Username field
+2. Login password field
+3. Submit button
+
+Select 'inspect' and 'copy selector'
+Next, navigate back here and paste the selector one by one.
+
+Please enter “username field” selector: #email_address
+Please enter “login password field” selector: #password
+Please enter “submit button” selector: #page-top > div.view.flex.flex-column.min-vh-100.db-pr > div.flex-grow-1.flex-shrink-0.flex-basis-auto.flex.flex-column > main > div.relative.z-1.mw6-l.center-l > div > form > button
+Scanning website...
+
+#The crawler will then start scraping from the file link provided above.
+#Console results
+
+user@user-MacBook-Pro purple-hats %
+```
+
+
+
+
+
+

combine.js

@@ -1,5 +1,6 @@
 const { crawlSitemap } = require('./crawlers/crawlSitemap');
 const { crawlDomain } = require('./crawlers/crawlDomain');
+
 const { mergeFiles } = require('./mergeAxeResults');
 const { getHostnameFromRegex, createAndUpdateFolders } = require('./utils');
 const { a11yStorage } = require('./constants/constants');
@@ -14,6 +15,7 @@ exports.combineRun = async details => {
     envDetails = {
       type: process.env.TYPE,
       url: process.env.URL,
+
       randomToken: process.env.RANDOMTOKEN,
     };
   }

crawlers/__tests__/commonCrawlerFunc.test.js

@@ -0,0 +1,63 @@
+const rewire = require("rewire");
+const { gotoFunction } = require('../commonCrawlerFunc');
+
+describe('test filter axe results', () => {
+  test('it works', () => {
+    const privateFuncs = rewire('../commonCrawlerFunc');
+    const filterAxeResults = privateFuncs.__get__('filterAxeResults');
+
+    const host = "http://test.com/";
+    const results = {
+      violations: [{
+        id: "1",
+        nodes: [{ html: "1-html1" }, { html: "1-html2" }],
+        help: "help1",
+        impact: "impact1",
+        helpUrl: "helpurl1"
+      },
+      {
+        id: "2",
+        nodes: [{ html: "2-html1" }, { html: "2-html2" }],
+        help: "help2",
+        impact: "impact2",
+        helpUrl: "helpurl2"
+      }],
+      url: `${host}api/path`
+    }
+
+    const { url, page, errors } = filterAxeResults(results, host);
+
+    expect(url).toEqual(results.url)
+    expect(page).toEqual('api/path');
+    expect(errors).toEqual([
+      {
+        id: "1",
+        description: "help1",
+        impact: "impact1",
+        helpUrl: "helpurl1",
+        fixes: [{ htmlElement: "1-html1" }, { htmlElement: "1-html2" }]
+      },
+      {
+        id: "2",
+        description: "help2",
+        impact: "impact2",
+        helpUrl: "helpurl2",
+        fixes: [{ htmlElement: "2-html1" }, { htmlElement: "2-html2" }]
+      }
+    ]);
+  });
+});
+
+describe('test goto function', () => {
+  test('it works', async () => {
+    const goToResponse = "response";
+    const request = { url: "url" };
+    const page = { goto: jest.fn(() => goToResponse) };
+
+    const result = await gotoFunction({ request, page });
+
+    expect(result).toEqual(goToResponse);
+    expect(page.goto.mock.calls.length).toEqual(1);
+    expect(page.goto.mock.calls[0]).toEqual([request.url, { waitUntil: 'networkidle2' }, { timeout: 30000 }]);
+  });
+});

installers/linux-installer.sh

@@ -1,7 +1,5 @@
 #!/bin/bash
 
-#Linux in general
-
 # Removing previous installation of /.nvm directory and node_modules
 if [ -d "node_modules" ]; then
    rm -r node_modules

jest.config.js

@@ -0,0 +1,200 @@
+// For a detailed explanation regarding each configuration property, visit:
+// https://jestjs.io/docs/en/configuration.html
+
+module.exports = {
+  // All imported modules in your tests should be mocked automatically
+  // automock: false,
+
+  // Stop running tests after `n` failures
+  // bail: 0,
+
+  // The directory where Jest should store its cached dependency information
+  // cacheDirectory: "/private/var/folders/rf/fq1pl5kj1278tskrsgv4hrt00000gn/T/jest_dx",
+
+  // Automatically clear mock calls and instances between every test
+  clearMocks: true,
+
+  // Indicates whether the coverage information should be collected while executing the test
+  collectCoverage: true,
+
+  // An array of glob patterns indicating a set of files for which coverage information should be collected
+  collectCoverageFrom: [
+    "**/*.{js,jsx}",
+    "!**/node_modules/**"
+  ],
+
+  // The directory where Jest should output its coverage files
+  coverageDirectory: "coverage",
+
+  // An array of regexp pattern strings used to skip coverage collection
+  // coveragePathIgnorePatterns: [
+  //   "/node_modules/"
+  // ],
+
+  // Indicates which provider should be used to instrument code for coverage
+  coverageProvider: "v8",
+
+  // A list of reporter names that Jest uses when writing coverage reports
+  coverageReporters: [
+    "text",
+    "text-summary"
+  ],
+
+  // An object that configures minimum threshold enforcement for coverage results
+  coverageThreshold: {
+    "global": {
+      "branches": 1,
+      "functions": 1,
+      "lines": 1,
+      "statements": 1
+    },
+  },
+
+  // A path to a custom dependency extractor
+  // dependencyExtractor: undefined,
+
+  // Make calling deprecated APIs throw helpful error messages
+  // errorOnDeprecated: false,
+
+  // Force coverage collection from ignored files using an array of glob patterns
+  // forceCoverageMatch: [],
+
+  // A path to a module which exports an async function that is triggered once before all test suites
+  // globalSetup: undefined,
+
+  // A path to a module which exports an async function that is triggered once after all test suites
+  // globalTeardown: undefined,
+
+  // A set of global variables that need to be available in all test environments
+  // globals: {},
+
+  // The maximum amount of workers used to run your tests. Can be specified as % or a number. E.g. maxWorkers: 10% will use 10% of your CPU amount + 1 as the maximum worker number. maxWorkers: 2 will use a maximum of 2 workers.
+  // maxWorkers: "50%",
+
+  // An array of directory names to be searched recursively up from the requiring module's location
+  // moduleDirectories: [
+  //   "node_modules"
+  // ],
+
+  // An array of file extensions your modules use
+  // moduleFileExtensions: [
+  //   "js",
+  //   "json",
+  //   "jsx",
+  //   "ts",
+  //   "tsx",
+  //   "node"
+  // ],
+
+  // A map from regular expressions to module names or to arrays of module names that allow to stub out resources with a single module
+  // moduleNameMapper: {},
+
+  // An array of regexp pattern strings, matched against all module paths before considered 'visible' to the module loader
+  // modulePathIgnorePatterns: [],
+
+  // Activates notifications for test results
+  // notify: false,
+
+  // An enum that specifies notification mode. Requires { notify: true }
+  // notifyMode: "failure-change",
+
+  // A preset that is used as a base for Jest's configuration
+  // preset: undefined,
+
+  // Run tests from one or more projects
+  // projects: undefined,
+
+  // Use this configuration option to add custom reporters to Jest
+  // reporters: undefined,
+
+  // Automatically reset mock state between every test
+  // resetMocks: false,
+
+  // Reset the module registry before running each individual test
+  // resetModules: false,
+
+  // A path to a custom resolver
+  // resolver: undefined,
+
+  // Automatically restore mock state between every test
+  // restoreMocks: false,
+
+  // The root directory that Jest should scan for tests and modules within
+  // rootDir: undefined,
+
+  // A list of paths to directories that Jest should use to search for files in
+  // roots: [
+  //   "<rootDir>"
+  // ],
+
+  // Allows you to use a custom runner instead of Jest's default test runner
+  // runner: "jest-runner",
+
+  // The paths to modules that run some code to configure or set up the testing environment before each test
+  // setupFiles: [],
+
+  // A list of paths to modules that run some code to configure or set up the testing framework before each test
+  // setupFilesAfterEnv: [],
+
+  // The number of seconds after which a test is considered as slow and reported as such in the results.
+  // slowTestThreshold: 5,
+
+  // A list of paths to snapshot serializer modules Jest should use for snapshot testing
+  // snapshotSerializers: [],
+
+  // The test environment that will be used for testing
+  testEnvironment: "node",
+
+  // Options that will be passed to the testEnvironment
+  // testEnvironmentOptions: {},
+
+  // Adds a location field to test results
+  // testLocationInResults: false,
+
+  // The glob patterns Jest uses to detect test files
+  // testMatch: [
+  //   "**/__tests__/**/*.[jt]s?(x)",
+  //   "**/?(*.)+(spec|test).[tj]s?(x)"
+  // ],
+
+  // An array of regexp pattern strings that are matched against all test paths, matched tests are skipped
+  // testPathIgnorePatterns: [
+  //   "/node_modules/"
+  // ],
+
+  // The regexp pattern or array of patterns that Jest uses to detect test files
+  // testRegex: [],
+
+  // This option allows the use of a custom results processor
+  // testResultsProcessor: undefined,
+
+  // This option allows use of a custom test runner
+  // testRunner: "jasmine2",
+
+  // This option sets the URL for the jsdom environment. It is reflected in properties such as location.href
+  // testURL: "http://localhost",
+
+  // Setting this value to "fake" allows the use of fake timers for functions such as "setTimeout"
+  // timers: "real",
+
+  // A map from regular expressions to paths to transformers
+  // transform: undefined,
+
+  // An array of regexp pattern strings that are matched against all source file paths, matched files will skip transformation
+  // transformIgnorePatterns: [
+  //   "/node_modules/",
+  //   "\\.pnp\\.[^\\/]+$"
+  // ],
+
+  // An array of regexp pattern strings that are matched against all modules before the module loader will automatically return a mock for them
+  // unmockedModulePathPatterns: undefined,
+
+  // Indicates whether each individual test should be reported during the run
+  // verbose: undefined,
+
+  // An array of regexp patterns that are matched against all source file paths before re-running tests in watch mode
+  // watchPathIgnorePatterns: [],
+
+  // Whether to use watchman for file crawling
+  // watchman: true,
+};