File size: 7,209 Bytes
ccad850 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"sData = [] # sinhala data tuple\n",
"eData = [] # english data tuple\n",
"\n",
"lstword = []\n",
"final = []\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"\n",
"import pickle\n",
"import TranslaterLogic\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def clearlstword():\n",
" global lstword\n",
" lstword = []\n",
"\n",
"\n",
"def translate(txt,t):\n",
" global lstword\n",
" lstword.clear()\n",
" if len(txt)==0:\n",
" return lstword\n",
" else:\n",
" l=t.printAutoSuggestions(txt, 2)\n",
" #if len(txt) >= 5:\n",
" # t.printAutoSuggestions(txt, 1)\n",
" #else:\n",
" # t.printAutoSuggestions(txt, 2)\n",
" #print(lstword)\n",
" return l\n",
"\n",
"\n",
"class TrieNode():\n",
" def __init__(self):\n",
" # Initialising one node for trie\n",
" self.children = {}\n",
" self.last = False\n",
"\n",
"\n",
"class Trie():\n",
"\n",
" def __init__(self):\n",
"\n",
" # Initialising the trie structure.\n",
" self.root = TrieNode()\n",
"\n",
" def formTrie(self, keys):\n",
"\n",
" # Forms a trie structure with the given set of strings\n",
" # if it does not exists already else it merges the key\n",
" # into it by extending the structure as required\n",
" for key in keys:\n",
" self.insert(key) # inserting one key to the trie.\n",
"\n",
" def insert(self, key):\n",
"\n",
" # Inserts a key into trie if it does not exist already.\n",
" # And if the key is a prefix of the trie node, just\n",
" # marks it as leaf node.\n",
" node = self.root\n",
"\n",
" for a in key:\n",
" if not node.children.get(a):\n",
" node.children[a] = TrieNode()\n",
"\n",
" node = node.children[a]\n",
"\n",
" node.last = True\n",
"\n",
" def suggestionsRec(self, node, word):\n",
"\n",
" # Method to recursively traverse the trie\n",
" # and return a whole word.\n",
" lstword=[]\n",
" \n",
" if node.last:\n",
" sin_indexes = [n for n, x in enumerate(eData) if x == word]\n",
" for i in sin_indexes:\n",
" y = int(i)\n",
" if sData[y] not in lstword:\n",
" # print(sData[y])\n",
" lstword.append(sData[y])\n",
" #adding the rule\n",
" #txt=str(TranslaterLogic.convertText(word))\n",
" # print(txt)\n",
" #lstword.append(txt)\n",
" return lstword\n",
" \n",
" def suggestionsRecsuffix(self, node, word):\n",
"\n",
" # Method to recursively traverse the trie\n",
" # and return a whole word.\n",
" if node.last:\n",
" sin_indexes = [n for n, x in enumerate(eData) if x == word]\n",
" for i in sin_indexes:\n",
" y = int(i)\n",
" if sData[y] not in lstword:\n",
" # print(sData[y])\n",
" lstword.append(sData[y])\n",
"\n",
" for a, n in node.children.items():\n",
" self.suggestionsRec(n, word + a)\n",
"\n",
" def printAutoSuggestions(self, key, para):\n",
"\n",
" # adding text using rule\n",
" # lstword.append(str(TranslaterLogic.convertText(key)))\n",
"\n",
" # Returns all the words in the trie whose common\n",
" # prefix is the given key thus listing out all\n",
" # the suggestions for autocomplete.\n",
"\n",
" node = self.root\n",
"\n",
" for a in key:\n",
" # no string in the Trie has this prefix\n",
" if not node.children.get(a):\n",
" return 0\n",
" node = node.children[a]\n",
"\n",
" # If prefix is present as a word, but\n",
" # there is no subtree below the last\n",
" # matching node.\n",
" if not node.children:\n",
" return -1\n",
" if para == 1:\n",
" lst=self.suggestionsRecsuffix(node, key)\n",
" return lst\n",
" else:\n",
" lst=self.suggestionsRec(node, key)\n",
" return lst"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# Code for creating trie\n",
"\n",
"textFile = open(\"singlishtrainsuggest.txt\",\n",
" mode='r', encoding='utf-8')\n",
"for i in textFile:\n",
" txt = i.split(\"/\")\n",
" eData.append(txt[0])\n",
" sData.append(txt[1].strip('\\n'))\n",
"\n",
"keys = eData\n",
"# keys to form the trie structure.\n",
"# creating trie object\n",
"t = Trie()\n",
"\n",
"# creating the trie structure with the\n",
"# given set of strings.\n",
"# t.formTrie(keys)\n",
"# print(\"Trie generated .\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Trie saved.\n"
]
}
],
"source": [
"# import pickle\n",
"\n",
"# # Saving the Trie object\n",
"# with open('trie.pkl', 'wb') as f:\n",
"# pickle.dump(t, f)\n",
"\n",
"# print(\"Trie saved.\")\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Trie loaded.\n"
]
}
],
"source": [
"import pickle\n",
"# Loading the Trie object\n",
"with open('trie.pkl', 'rb') as f:\n",
" loaded_t = pickle.load(f)\n",
"\n",
"print(\"Trie loaded.\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ආදරය', 'ආදාරය', 'අදාරය', 'ආධාරය', 'අදරය']\n"
]
}
],
"source": [
"print(translate(\"adaraya\",loaded_t))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "llm",
"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": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|