RishabhMakhar-Module4

Problem-1/Problem-1unittesting.txt

@@ -0,0 +1,89 @@
+Test case 1-Valid URL and words file:
+Input:
+A valid URL text file that contains one URL per line.
+A valid words text file that contains one word per line.
+Output:
+The top three words with their frequency for each URL in the URL file.
+The total frequency of each word from all URLs combined.
+
+https: //github.con/hotwax/training-assignment/wiki/Module—2-Implementation
+is 4
+the 4
+cricket 0
+
+https: //um.espncricinfo.con/
+
+is 4
+cricket 25
+the 2
+
+https://www.google.com/search?q=football&oq=football&aqs=chrome..69i57j0i67i433l4j46i67i433j0i67i433l3j0i67.2762j0j4&sourceid=chrome&ie=UTF-8
+
+is 0
+the 12
+cricket 0
+
+
+cricket 25
+is 8
+the 18
+=====================================================================================================================================================================================
+
+
+Test case 2-Invalid URL file:
+Input:
+An invalid URL text file that does not exist or is empty.
+A valid words text file that contains one word per line.
+Output:the file cannot be read or is empty.
+
+
+Test case 3-Invalid words file:
+Input:
+A valid URL text file that contains one URL per line.
+An invalid words text file that does not exist or is empty.
+Output:
+the file cannot be read or is empty.
+
+
+Test case 4-Invalid URL:
+Input:
+A valid URL text file that contains one URL per line.
+A valid words text file that contains one word per line.
+One or more invalid URLs in the URL file.
+Output:
+The top three words with their frequency for each valid URL in the URL file.
+invalid URL indicating that it cannot be parsed.
+
+
+Test case 5-Invalid word:
+Input:
+A valid URL text file that contains one URL per line.
+A valid words text file that contains one or more invalid words.
+Output:
+The top three words with their frequency for each URL in the URL file, excluding the invalid words.
+The total frequency of each valid word from all URLs combined.
+
+
+Test case 6-Invalid input type:
+Input:
+A valid URL text file that contains one URL per line.
+A valid words text file that contains one word per line.
+One or both of the input files are not in the correct format (e.g. a PDF file instead of a text file).
+Output:
+the file format is incorrect.
+
+
+Test case 7-Edge case: Empty URL file:
+Input:
+An empty URL text file.
+A valid words text file that contains one word per line.
+Output:
+the URL file is empty.
+
+
+Test case 8-Edge case: Empty words file:
+Input:
+A valid URL text file that contains one URL per line.
+An empty words text file.
+Output:
+the words file is empty.

Problem-1/package.json

@@ -0,0 +1,13 @@
+{
+    "name": "employees",
+    "version": "1.0.0",
+    "type": "module",
+    "dependencies": {
+        "axios": "^1.3.5",
+        "cheerio": "^1.0.0-rc.3",
+        "fs": "^0.0.1-security",
+        "request": "^2.88.2",
+        "readline": "1.3.0",
+        "request-promise-native": "^1.0.9"
+    }
+}

Problem-1/urls.txt

@@ -0,0 +1,3 @@
+ https://github.com/hotwax/training-assignment/wiki/Module---2-Implementation
+ https://www.espncricinfo.com/
+ https://www.google.com/search?q=football&oq=football&aqs=chrome..69i57j0i67i433l4j46i67i433j0i67i433l3j0i67.2762j0j4&sourceid=chrome&ie=UTF-8

Problem-1/webscrapper.js

@@ -0,0 +1,85 @@
+// Import necessary packages
+import fs from "fs";
+import cheerio from "cheerio";
+import axios from "axios";
+
+// Define file paths for URLs and words
+const urlsPath = 'urls.txt'; 
+const wordsPath = 'words.txt'; 
+
+// Initialize arrays for URLs and words
+let words=[];
+let urls=[];
+
+try { 
+    // Read URLs from file
+    urls = fs.readFileSync(urlsPath, 'utf-8').split('\n').filter(url => url.trim() !== ''); 
+} catch(error) {
+    // Handle error reading URLs from file
+    console.log(error);
+}
+
+try {
+    // Read words from file
+    words = fs.readFileSync(wordsPath, 'utf-8').split('\n').filter(word => word.trim() !== ''); 
+} catch(error) {
+    // Handle error reading words from file
+    console.log(error);
+}
+
+// Initialize an empty object to store the count of each word
+const wordCounts = {}; 
+
+// Define function to count occurrences of a word in a string
+function countOccurrences(string, word) {
+  const regex = new RegExp(word, 'gi');
+  return (string.match(regex) || []).length;
+}
+
+// Define an asynchronous main function to perform the web scraping and word counting
+const main = async () => {
+  return new Promise(async (resolve, reject) => {
+    // Check that there are URLs and words to process
+    if (urls.length == 0) {
+      reject("urls file is empty");
+      return;
+    }
+    if (words.length == 0) {
+      reject("words file is empty");
+      return;
+    }
+    // Loop through each URL and scrape its text content
+    for (const url of urls) {
+      const body = await axios.get(url);
+      const $ = cheerio.load(body.data);
+      const text = $('body').text().toLowerCase();
+      const counts = {};
+      // Loop through each word and count its occurrences in the scraped text
+      for (const word of words) {
+        const woords = word.replace(/\r*/g, '');
+        const count = countOccurrences(text, woords.toLowerCase());
+        counts[woords] = count;
+        // If the word hasn't been seen before, add it to the total word count
+        if (!wordCounts[woords]) {
+          wordCounts[woords] = count;
+        } else {
+          // If the word has been seen before, add its count to the total count
+          wordCounts[woords] += count;
+        }
+      };
+      // Sort the word counts in descending order and print the top three words for the URL
+      const sortedCounts = Object.entries(counts).sort((value1, value2) => value2[1] - value1[1]);
+      const topWords = sortedCounts.slice(0, 3).map(entry => entry[0] + ' - ' + entry[1]);
+      console.log(url + '\n' + topWords.join('\n') + '\n');
+    };
+    resolve(wordCounts);
+  });
+}
+
+// Call the main function and store the result in a variable
+const data = await main();
+
+// Sort the total word counts in descending order and print them
+const sortedWordCounts = Object.entries(data).sort((value1, value2) => value2[1] - value1[1]);
+console.log('Total word counts:\n');
+sortedWordCounts.forEach(entry => console.log(entry[0] + ' - ' + entry[1]));

Problem-1/words.txt

@@ -0,0 +1,3 @@
+is
+the
+cricket

Problem-4/Problem-4unittesting.txt

@@ -0,0 +1,92 @@
+-Test Case 1: Serialization
+Input:
+Option 1 (for Serialize file)
+test.json (file name)
+Output:
+Serialization done successfully.
+
+The 'test.json' file should contain the serialized data of the student objects in JSON format.
+
+
+
+-Test Case 2: Deserialization
+Input:
+Option 2 (for Deserialize file)
+test.json (file name)
+Output:
+Deserialization done successfully.
+[ Student {
+firstName: 'Rishabh',
+dateOfBirth: 1990-01-01T00:00:00.000Z,
+address: Address {
+city: 'Indore',
+state: 'MP',
+pinCode: 452001,
+country: 'India'
+}
+},
+Student {
+firstName: 'Sarthak',
+dateOfBirth: 1992-02-02T00:00:00.000Z,
+address: Address {
+city: 'Bhopal',
+state: 'MP',
+pinCode: 452045,
+country: 'India'
+}
+},
+Student {
+firstName: 'Vaibhav',
+dateOfBirth: 2001-01-01T00:00:00.000Z,
+address: Address {
+city: 'Ujjain',
+state: 'MP',
+pinCode: 452076,
+country: 'India'
+}
+},
+Student {
+firstName: 'Nayan',
+dateOfBirth: 2001-01-01T00:00:00.000Z,
+address: Address {
+city: 'Dewas',
+state: 'MP',
+pinCode: 452087,
+country: 'India'
+}
+} ]
+
+The output should contain the deserialized student objects with their properties.
+
+
+
+-Test Case 3: File not found
+Input:
+Option 2 (for Deserialize file)
+test1.json (non-existent file name)
+Output:
+File not found.
+
+The code should handle the error if the file specified for deserialization does not exist.
+
+
+
+-Test Case4: Invalid choice
+Input:
+Option 4 (an invalid choice)
+Output:
+Invalid choice.
+
+The code should handle the error if the user enters an invalid choice.
+
+
+
+-Test Case 5: Invalid date format
+Input:
+Option 1 (for Serialize file)
+test.json (file name)
+1990-01-01T00:00:00.000Z (invalid date format)
+Output:
+Serialization done successfully.
+
+The 'test.json' file should contain the serialized data of the student objects in JSON format, with the invalid date format handled by the code.

Problem-4/output1.ser

@@ -0,0 +1 @@
+[{"firstName":"Rishabh","dateOfBirth":"1990-01-01T00:00:00.000Z","address":{"city":"Indore","state":"MP","pinCode":452001,"country":"India"}},{"firstName":"Sarthak","dateOfBirth":"1992-02-02T00:00:00.000Z","address":{"city":"Bhopal","state":"MP","pinCode":452045,"country":"India"}},{"firstName":"Vaibhav","dateOfBirth":"2001-01-01T00:00:00.000Z","address":{"city":"Ujjain","state":"MP","pinCode":452076,"country":"India"}},{"firstName":"Nayan","dateOfBirth":"2001-01-01T00:00:00.000Z","address":{"city":"Dewas","state":"MP","pinCode":452087,"country":"India"}}]

Problem-4/output2.ser

@@ -0,0 +1 @@
+[{"firstName":"Rishabh","dateOfBirth":"1990-01-01T00:00:00.000Z","address":{"city":"Indore","state":"MP","pinCode":452001,"country":"India"}},{"firstName":"Sarthak","dateOfBirth":"1992-02-02T00:00:00.000Z","address":{"city":"Bhopal","state":"MP","pinCode":452045,"country":"India"}},{"firstName":"Vaibhav","dateOfBirth":"2001-01-01T00:00:00.000Z","address":{"city":"Ujjain","state":"MP","pinCode":452076,"country":"India"}},{"firstName":"Nayan","dateOfBirth":"2001-01-01T00:00:00.000Z","address":{"city":"Dewas","state":"MP","pinCode":452087,"country":"India"}}]

Problem-4/package.json

@@ -0,0 +1,19 @@
+{
+    "name": "nodejs",
+    "version": "1.0.0",
+    "description": "",
+    "main": "index.js",
+    "scripts": {
+        "test": "echo \"Error: no test specified\" && exit 1"
+    },
+    "keywords": [],
+    "author": "",
+    "license": "ISC",
+    "dependencies": {
+        "@types/node": "^18.0.6",
+        "axios": "^1.3.4",
+        "cheerio": "^1.0.0-rc.12",
+        "node-fetch": "^3.2.6",
+        "request": "^2.88.2"
+    }
+}