{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "5912ba94-833f-4662-8b8c-f201b5dde892", "metadata": {}, "outputs": [], "source": [ "# # Function to process \"double\" followed by a number\n", "# def process_doubles(sentence):\n", "# tokens = sentence.split()\n", "# result = []\n", "# i = 0\n", "# while i < len(tokens):\n", "# if tokens[i] == \"डबल\":\n", "# if i + 1 < len(tokens):\n", "# result.append(tokens[i + 1])\n", "# result.append(tokens[i + 1])\n", "# i += 2\n", "# else:\n", "# result.append(tokens[i])\n", "# i += 1\n", "# else:\n", "# result.append(tokens[i])\n", "# i += 1\n", "# return ' '.join(result)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "7d7065ce-94c9-4cda-a398-71dac90a67ba", "metadata": {}, "outputs": [], "source": [ "import re\n", "\n", "def process_doubles(sentence):\n", " # Use regex to split 'डबल' followed by numbers/words without space (e.g., \"डबलवन\" -> \"डबल वन\")\n", " sentence = re.sub(r'(डबल)(\\S+)', r'\\1 \\2', sentence)\n", " \n", " tokens = sentence.split()\n", " result = []\n", " i = 0\n", " \n", " while i < len(tokens):\n", " if tokens[i] == \"डबल\":\n", " if i + 1 < len(tokens):\n", " result.append(tokens[i + 1]) # Append the next word/number\n", " result.append(tokens[i + 1]) # Append the next word/number again to duplicate\n", " i += 2 # Skip over the next word since it's already processed\n", " else:\n", " result.append(tokens[i])\n", " i += 1\n", " else:\n", " result.append(tokens[i])\n", " i += 1\n", "\n", " return ' '.join(result)\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.7" } }, "nbformat": 4, "nbformat_minor": 5 }