feat: add imdb and ag news dataset to datasets

README.md

@@ -22,3 +22,10 @@ Furthermore, it investigates two different scheduling policies to send request t
 ## Getting Started
 To run the experiments, open `index.html` in a web browser. Ensure that you have an API key for the OpenRouter service to run the cloud inference.
 You can then download the models and run them in the browser by leveraging the transformers.js library.
+
+
+## Dataset preparation
+To prepare the dataset for the experiments, we follow these steps:
+- Download the dataset from kaggle or huggingface
+- Add row indexes to each entry in the dataset for easy reference
+- Save the prepared dataset in the `dataset/` directory

dataset/preprocess_datasets.ipynb

@@ -0,0 +1,523 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:54:53.050054Z",
+     "start_time": "2025-12-25T10:54:49.296474Z"
+    }
+   },
+   "source": "import pandas as pd",
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "# Prepare the spam/ham email dataset",
+   "id": "fd1d0f3beb9aa893"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-21T16:20:15.450476Z",
+     "start_time": "2025-12-21T16:20:15.389394Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset = pd.read_csv('./emails.csv')",
+   "id": "f72a26d75f7a2588",
+   "outputs": [],
+   "execution_count": 11
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-21T16:20:15.562018Z",
+     "start_time": "2025-12-21T16:20:15.550178Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add column with row id\n",
+    "dataset['ID'] = range(1, len(dataset) + 1)"
+   ],
+   "id": "e6a938ba1a501431",
+   "outputs": [],
+   "execution_count": 12
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-21T16:20:15.714419Z",
+     "start_time": "2025-12-21T16:20:15.710137Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add the column to the first position\n",
+    "cols = dataset.columns.tolist()\n",
+    "cols = cols[-1:] + cols[:-1]\n",
+    "dataset = dataset[cols]"
+   ],
+   "id": "9d56f16fc000b2e2",
+   "outputs": [],
+   "execution_count": 13
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-21T16:20:15.896626Z",
+     "start_time": "2025-12-21T16:20:15.883918Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset.head()",
+   "id": "c853a292fe6d4d01",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "   ID                                               Text  Spam\n",
+       "0   1  Subject: naturally irresistible your corporate...     1\n",
+       "1   2  Subject: the stock trading gunslinger  fanny i...     1\n",
+       "2   3  Subject: unbelievable new homes made easy  im ...     1\n",
+       "3   4  Subject: 4 color printing special  request add...     1\n",
+       "4   5  Subject: do not have money , get software cds ...     1"
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ID</th>\n",
+       "      <th>Text</th>\n",
+       "      <th>Spam</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Subject: naturally irresistible your corporate...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Subject: the stock trading gunslinger  fanny i...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Subject: unbelievable new homes made easy  im ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Subject: 4 color printing special  request add...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Subject: do not have money , get software cds ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 14
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-21T16:20:33.041536Z",
+     "start_time": "2025-12-21T16:20:32.900818Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# store csv in dataset folder\n",
+    "dataset.to_csv('./spam_ham_dataset.csv', index=False)"
+   ],
+   "id": "2bc331812feedf10",
+   "outputs": [],
+   "execution_count": 15
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "# Prepare the AG news dataset",
+   "id": "ec3f208efcc1eeda"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:56:01.120606Z",
+     "start_time": "2025-12-25T10:56:00.990306Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset = pd.read_csv('./ag_news_test.csv')",
+   "id": "6396678647ac4f8",
+   "outputs": [],
+   "execution_count": 2
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:56:05.735124Z",
+     "start_time": "2025-12-25T10:56:05.722137Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add column with row id\n",
+    "dataset['ID'] = range(1, len(dataset) + 1)"
+   ],
+   "id": "445a51aa7a9d6de9",
+   "outputs": [],
+   "execution_count": 3
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:56:10.368440Z",
+     "start_time": "2025-12-25T10:56:10.320560Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add the column to the first position\n",
+    "cols = dataset.columns.tolist()\n",
+    "cols = cols[-1:] + cols[:-1]\n",
+    "dataset = dataset[cols]"
+   ],
+   "id": "a945120ba657ceaa",
+   "outputs": [],
+   "execution_count": 4
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:56:12.070628Z",
+     "start_time": "2025-12-25T10:56:12.039268Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset.head()",
+   "id": "3c95d325ace568ef",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "   ID  Class Index                                              Title  \\\n",
+       "0   1            3                  Fears for T N pension after talks   \n",
+       "1   2            4  The Race is On: Second Private Team Sets Launc...   \n",
+       "2   3            4      Ky. Company Wins Grant to Study Peptides (AP)   \n",
+       "3   4            4      Prediction Unit Helps Forecast Wildfires (AP)   \n",
+       "4   5            4        Calif. Aims to Limit Farm-Related Smog (AP)   \n",
+       "\n",
+       "                                         Description  \n",
+       "0  Unions representing workers at Turner   Newall...  \n",
+       "1  SPACE.com - TORONTO, Canada -- A second\\team o...  \n",
+       "2  AP - A company founded by a chemistry research...  \n",
+       "3  AP - It's barely dawn when Mike Fitzpatrick st...  \n",
+       "4  AP - Southern California's smog-fighting agenc...  "
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ID</th>\n",
+       "      <th>Class Index</th>\n",
+       "      <th>Title</th>\n",
+       "      <th>Description</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Fears for T N pension after talks</td>\n",
+       "      <td>Unions representing workers at Turner   Newall...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>The Race is On: Second Private Team Sets Launc...</td>\n",
+       "      <td>SPACE.com - TORONTO, Canada -- A second\\team o...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Ky. Company Wins Grant to Study Peptides (AP)</td>\n",
+       "      <td>AP - A company founded by a chemistry research...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Prediction Unit Helps Forecast Wildfires (AP)</td>\n",
+       "      <td>AP - It's barely dawn when Mike Fitzpatrick st...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Calif. Aims to Limit Farm-Related Smog (AP)</td>\n",
+       "      <td>AP - Southern California's smog-fighting agenc...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 5
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:56:34.202882Z",
+     "start_time": "2025-12-25T10:56:34.156909Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# store csv in dataset folder\n",
+    "dataset.to_csv('./ag_news_test.csv', index=False)"
+   ],
+   "id": "d62c782d061d0427",
+   "outputs": [],
+   "execution_count": 6
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "# Prepare the IMDB reviews dataset",
+   "id": "d6d26cc073ed9c20"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:57:20.086793Z",
+     "start_time": "2025-12-25T10:57:19.626919Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset = pd.read_csv('./imdb_dataset.csv')",
+   "id": "d428b1226c135eeb",
+   "outputs": [],
+   "execution_count": 7
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:57:21.530556Z",
+     "start_time": "2025-12-25T10:57:21.516704Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add column with row id\n",
+    "dataset['ID'] = range(1, len(dataset) + 1)"
+   ],
+   "id": "fcd59bb4a4faaee9",
+   "outputs": [],
+   "execution_count": 8
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:57:23.603144Z",
+     "start_time": "2025-12-25T10:57:23.588206Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# add the column to the first position\n",
+    "cols = dataset.columns.tolist()\n",
+    "cols = cols[-1:] + cols[:-1]\n",
+    "dataset = dataset[cols]"
+   ],
+   "id": "4f484cca1f2663f3",
+   "outputs": [],
+   "execution_count": 9
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:57:24.466785Z",
+     "start_time": "2025-12-25T10:57:24.448227Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "dataset.head()",
+   "id": "c8a8d1415d414af3",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "   ID                                             review sentiment\n",
+       "0   1  One of the other reviewers has mentioned that ...  positive\n",
+       "1   2  A wonderful little production. <br /><br />The...  positive\n",
+       "2   3  I thought this was a wonderful way to spend ti...  positive\n",
+       "3   4  Basically there's a family where a little boy ...  negative\n",
+       "4   5  Petter Mattei's \"Love in the Time of Money\" is...  positive"
+      ],
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ID</th>\n",
+       "      <th>review</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>One of the other reviewers has mentioned that ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>A wonderful little production. &lt;br /&gt;&lt;br /&gt;The...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>I thought this was a wonderful way to spend ti...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Basically there's a family where a little boy ...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Petter Mattei's \"Love in the Time of Money\" is...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 10
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-12-25T10:57:38.303913Z",
+     "start_time": "2025-12-25T10:57:37.271989Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# store csv in dataset folder\n",
+    "dataset.to_csv('./imdb_dataset.csv', index=False)"
+   ],
+   "id": "df642952f75ee514",
+   "outputs": [],
+   "execution_count": 11
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

index.html

@@ -125,6 +125,8 @@
                         class="mt-1 w-full px-3 py-2 rounded-lg border border-gray-300 focus:ring-2 focus:ring-blue-500 focus:outline-none">
                     <option value="boolq_validation">BoolQ</option>
                     <option value="spam_ham_dataset">Spam</option>
+                    <option value="imdb_dataset">IMDB</option>
+                    <option value="ag_news_test">AG News</option>
                 </select>
             </label>
 

src/datasetLoader.js

@@ -36,29 +36,24 @@ export class DatasetLoader {
                 this._dataset = lines
                     .filter(l => l.trim().length > 0)
                     .map(line => {
-                        let id, answer, full_prompt, question, context, text;
+                        let id, answer, full_prompt;
 
-                        // load different datasets based on name
-                        if (name === 'boolq_validation') {
-                            // parse line into fields handling quoted commas
-                            [id, question, answer, context] = this._parseCSVLine(line);
-
-                            // set the prompt
-                            full_prompt = `Question: ${question}
-                                        Context: ${context}
-                                        Instructions: Answer with ONLY the word "true" or "false". Do not provide any explanation or additional text.
-                                        Answer:`;
-                        } else if (name === 'spam_ham_dataset') {
-                            [id, text, answer] = this._parseCSVLine(line);
-
-                            // convert answer to string boolean
-                            answer = (answer.toLowerCase() === 'spam') ? 'true' : 'false';
-
-                            // set the prompt
-                            full_prompt = `Task: Determine whether the following message is spam or not.
-                                        Instructions: Answer with ONLY the word "true" or "false". Do not provide any explanation or additional text.
-                                        Message: ${text}
-                                        Answer:`;
+                        // load different datasets based on the dataset name
+                        switch (name) {
+                            case 'boolq_validation':
+                                ({id, full_prompt, answer} = this._loadBoolQLine(line));
+                                break;
+                            case 'spam_ham_dataset':
+                                ({id, full_prompt, answer} = this._loadSpamHamLine(line));
+                                break;
+                            case 'imdb_dataset':
+                                ({id, full_prompt, answer} = this._loadIMDBLine(line));
+                                break;
+                            case 'ag_news_test':
+                                ({id, full_prompt, answer} = this._loadAGNewsLine(line));
+                                break;
+                            default:
+                                throw new Error(`DatasetLoader: Unsupported dataset name '${name}'`);
                         }
 
                         return {id: id, prompt: full_prompt, groundTruth: answer};
@@ -73,6 +68,94 @@ export class DatasetLoader {
             });
     }
 
+
+    /**
+     * Load a single line from the BoolQ dataset and prepare the prompt
+     *
+     * @param line - A single line from the BoolQ CSV dataset
+     * @returns {{full_prompt: string, answer: *, id: *}}
+     * @private
+     */
+    _loadBoolQLine(line) {
+        // parse line into fields handling quoted commas
+        const [id, question, answer, context] = this._parseCSVLine(line);
+
+        // set the prompt
+        const full_prompt = `Question: ${question}
+                                        Context: ${context}
+                                        Instructions: Answer with ONLY the word "true" or "false". Do not provide any explanation or additional text.
+                                        Answer:`;
+
+        return {id, full_prompt, answer}
+    }
+
+
+    /**
+     * Load a single line from the SpamHam dataset and prepare the prompt
+     *
+     * @param line - A single line from the SpamHam CSV dataset
+     * @returns {{full_prompt: string, answer: (string), id: *}}
+     * @private
+     */
+    _loadSpamHamLine(line) {
+        let [id, text, answer] = this._parseCSVLine(line);
+
+        // convert answer to string boolean
+        answer = (answer.toLowerCase() === 'spam') ? 'true' : 'false';
+
+        // set the prompt
+        const full_prompt = `Task: Determine whether the following message is spam or not.
+                                        Instructions: Answer with ONLY the word "true" or "false". Do not provide any explanation or additional text.
+                                        Message: ${text}
+                                        Answer:`;
+
+        return {id, full_prompt, answer}
+    }
+
+
+    /**
+     * Load a single line from the IMDB dataset and prepare the prompt
+     *
+     * @param line - A single line from the IMDB CSV dataset
+     * @returns {{full_prompt: string, answer: *, id: *}}
+     * @private
+     */
+    _loadIMDBLine(line) {
+        let [id, review, answer] = this._parseCSVLine(line);
+
+        // set the prompt
+        const full_prompt = `Task: Determine whether the sentiment of the following review is positive or negative.
+                                        Instructions: Answer with ONLY the word "positive" or "negative". Do not provide any explanation or additional text.
+                                        Review: ${review}
+                                        Sentiment:`;
+
+        return {id, full_prompt, answer}
+    }
+
+
+    /**
+     * Load a single line from the AG News dataset and prepare the prompt
+     *
+     * @param line - A single line from the AG News CSV dataset
+     * @returns {{full_prompt: string, answer: *, id: *}}
+     * @private
+     */
+    _loadAGNewsLine(line) {
+        let [id, answer, title, description] = this._parseCSVLine(line);
+
+        // set the prompt
+        const full_prompt = `Task: Determine whether the following news article belong to world, sports, business or Sci/Tech category.
+                                        Categories: World (1), Sports (2), Business (3), Sci/Tech (4).
+                                        Instructions: Answer with ONLY the id (1,2,3 or 4) of the class. Do not provide any explanation or additional text.
+                                        News Title: ${title}
+                                        News Description: ${description}
+                                        `;
+
+        return {id, full_prompt, answer}
+    }
+
+
+
     /**
      * Parse a single CSV line into fields, handling quoted fields with commas
      *

src/utils.js

@@ -33,7 +33,7 @@ export function logTo(el, evt) {
         <td>${evt.totalLatency?.toFixed(2) || evt.latency?.toFixed(2) || 0}ms</td>
         <td>${evt.queueingTime?.toFixed(2) || 0}ms</td>
         <td>${evt.inferenceTime?.toFixed(2) || evt.latency?.toFixed(2) || 0}ms</td>
-        <td title="${evt.job.prompt}">${evt.job.prompt.substring(0, 30)}...</td>
+        <td title="${escapeHtml(evt.job.prompt)}">${escapeHtml(evt.job.prompt.substring(0, 30))}...</td>
         <td title="${evt.response || ''}">${(evt.response || '').substring(0, 30)}</td>
         <td>${evt.evalRes.exactMatch}</td>
     `;
@@ -41,6 +41,24 @@ export function logTo(el, evt) {
     el.scrollTop = el.scrollHeight;
 }
 
+/**
+ * Escapes HTML special characters in a string to prevent HTML injection
+ *
+ * @param str - Input string
+ * @returns {string} - Escaped string
+ */
+function escapeHtml(str) {
+    return str.replace(/[&<>"']/g, (char) => {
+        const escapeMap = {
+            '&': '&amp;',
+            '<': '&lt;',
+            '>': '&gt;',
+            '"': '&quot;',
+            "'": '&#039;',
+        };
+        return escapeMap[char];
+    });
+}
 
 /**
  * Approximates the number of words in a given text string