File size: 20,711 Bytes
eb57aa1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 |
import os
from .data_helper import DataHelper
from .normalizer import Normalizer
class FindStems():
def __init__(self):
self.dir_path = os.path.dirname(os.path.realpath(__file__)) + "/"
self.noun_lex_path = self.dir_path + "resource/stemmer/stem_lex.pckl"
self.verb_lex_path = self.dir_path + "resource/stemmer/verbStemDict.pckl"
self.verb_tense_map_path = self.dir_path + "resource/stemmer/stem_verbMap.pckl"
self.irregular_nouns_path = self.dir_path + "resource/stemmer/stem_irregularNounDict.pckl"
self.prefix_list_path = self.dir_path + "resource/stemmer/pishvand.txt"
self.postfix_list_path = self.dir_path + "resource/stemmer/pasvand.txt"
self.verb_tense_file_path = self.dir_path + "resource/stemmer/verb_tense.txt"
self.mokasar_noun_path = self.dir_path + "resource/stemmer/mokasar.txt"
self.data_helper = DataHelper()
if(os.path.isfile(self.noun_lex_path) and os.path.isfile(self.verb_lex_path)
and os.path.isfile(self.verb_tense_map_path) and os.path.isfile(self.irregular_nouns_path)):
self.noun_lexicon = self.data_helper.load_var(self.noun_lex_path)
self.verb_lexicon = self.data_helper.load_var(self.verb_lex_path)
self.verb_tense_map = self.data_helper.load_var(self.verb_tense_map_path)
self.irregular_nouns = self.data_helper.load_var(self.irregular_nouns_path)
self.verb_p2f_map, self.verb_f2p_map = self.verb_tense_map[0], self.verb_tense_map[1]
else:
self.mynormalizer = Normalizer()
self.noun_lexicon, self.verb_lexicon, \
self.verb_tense_map, self.irregular_nouns =\
self.data_helper.build_stem_dictionary(self.mynormalizer,
self.verb_tense_file_path,
self.mokasar_noun_path)
self.data_helper.save_var(save_path=self.noun_lex_path, variable=self.noun_lexicon)
self.data_helper.save_var(save_path=self.verb_lex_path, variable=self.verb_lexicon)
self.data_helper.save_var(save_path=self.verb_tense_map_path, variable=self.verb_tense_map)
self.data_helper.save_var(save_path=self.irregular_nouns_path, variable=self.irregular_nouns)
self.verb_p2f_map, self.verb_f2p_map = self.verb_tense_map[0], self.verb_tense_map[1]
self.prefix_list = set({})
with open(self.prefix_list_path, "r", encoding='utf-8') as pishvand_input_file:
pishvandFile_content = pishvand_input_file.readlines()
for el in pishvandFile_content:
self.prefix_list.add(el.strip())
self.postfix_list = set({})
with open(self.postfix_list_path, "r", encoding='utf-8') as pasvand_input_file:
pasvandFile_content = pasvand_input_file.readlines()
for el in pasvandFile_content:
self.postfix_list.add(el.strip())
def select_candidate(self, candidate_list, lexicon_set=None):
length = 1000
selected = ""
for tmp_candidate in candidate_list:
if lexicon_set == None and len(tmp_candidate) < length:
selected = tmp_candidate
length = len(tmp_candidate)
elif (lexicon_set != None) and (tmp_candidate in lexicon_set):
if(length == 1000):
selected = tmp_candidate
length = len(tmp_candidate)
else:
if(len(tmp_candidate) > length):
selected = tmp_candidate
length = len(tmp_candidate)
return selected
def is_prefix(self, word, prefix):
word = word.strip("\u200c")
return word.startswith(prefix)
def is_postfix(self, word, post):
word = word.strip("\u200c")
return word.endswith(post)
def remove_prefixes(self, word, prefix):
word = word.strip("\u200c")
candidateStem = set({})
for el in prefix:
if word.startswith(el):
if len(el) > 0:
tmp = word[len(el):].strip().strip('\u200c')
else:
tmp = word
candidateStem.add(tmp)
return candidateStem
def remove_postfixes(self, word, postfix):
word = word.strip("\u200c")
candidateStem = set({})
for el in postfix:
if word.endswith(el):
if len(el) > 0:
tmp = word[:-len(el)].strip().strip('\u200c')
else:
tmp = word
candidateStem.add(tmp)
return candidateStem
def map_irregular_noun(self, word):
if word in self.irregular_nouns:
return self.irregular_nouns[word]
else:
return word
def convert_to_stem(self, word, word_pos=None):
if word in self.noun_lexicon:
if (word_pos == None or word_pos == 'N'):
#print("in word dict...")
return self.map_irregular_noun(word)
elif word in self.verb_lexicon:
if word_pos is None or word_pos == 'V':
# print("in verb dict...")
if word in self.verb_f2p_map:
stem = self.verb_f2p_map[word] + "&" + word
elif word in self. verb_p2f_map:
stem = word + "&" + self.verb_p2f_map[word]
else:
stem = word
return stem
# if word is a verb
if word_pos is None or word_pos == "V":
# ماضی مستمر
candidate_list = self.remove_prefixes(word, ["داشتم", "داشتی", "داشت",
"داشتیم", "داشتید", "داشتند"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["می"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["یم", "ید", "ند",
"م", "ی", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# مضارع مستمر
candidate_list = self.remove_prefixes(word, ["دارم", "داری", "دارد",
"داریم", "دارید", "دارند"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["می"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["یم", "ید", "ند",
"م", "ی", "د"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_f2p_map:
stem = self.verb_f2p_map[new_word] + "&" + new_word
return stem
# مضارع اخباری
candidate_list = self.remove_prefixes(word, ["می", "نمی", "همی"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["یم", "ید", "ند",
"م", "ی", "د"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_f2p_map:
stem = self.verb_f2p_map[new_word] + "&" + new_word
return stem
# ماضی استمراری
candidate_list = self.remove_prefixes(word, ["می", "نمی", "همی"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["یم", "ید", "ند",
"م", "ی", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# ماضی بعید و التزامی
candidate_list = self.remove_postfixes(word, ["یم", "ید", "ند",
"م", "ی", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["بود", "باشد", "باش"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["ه"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["ن", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# ماضی نقلی
candidate_list = self.remove_postfixes(word, ["ام", "ای", "است",
"ایم", "اید", "اند"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["ه"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["ن", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# ماضی ابعد
candidate_list = self.remove_postfixes(word, ["ام", "ای", "است",
"ایم", "اید", "اند"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["ه"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["بود"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["ه"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["ن", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(new_word, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# آینده
candidate_list = self.remove_prefixes(word, ["خواه", "نخواه"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["یم", "ید", "ند",
"م", "ی", "د"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# مضارع التزامی و امر
candidate_list = self.remove_prefixes(word, ["ب", "ن", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_postfixes(new_word, ["یم", "ید", "ند", "م",
"ی", "د", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
if (self.is_prefix(new_word, "یا")) and (new_word not in self.verb_lexicon):
candidate_list = self.remove_prefixes(new_word, ["یا"])
new_word = self.select_candidate(candidate_list)
new_word = "آ" + new_word
if self.is_postfix(new_word, "آی") or self.is_postfix(new_word, "ای"):
if new_word not in self.verb_lexicon:
candidate_list = self.remove_postfixes(new_word, ["ی"])
new_word = self.select_candidate(candidate_list)
if self.is_prefix(new_word, "ی"):
candidate_list = self.remove_prefixes(new_word, ["ی"])
tmp_word = self.select_candidate(candidate_list)
if tmp_word and ("ا" + tmp_word) in self.verb_lexicon:
new_word = "ا" + tmp_word
if new_word and new_word in self.verb_lexicon:
if new_word in self.verb_f2p_map:
stem = self.verb_f2p_map[new_word] + "&" + new_word
return stem
# ماضی ساده
candidate_list = self.remove_postfixes(word, ["م", "ی", "",
"یم", "ید", "ند"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
candidate_list = self.remove_prefixes(new_word, ["ن", ""])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
# حالت مصدر
candidate_list = self.remove_postfixes(word, ["ن"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list, self.verb_lexicon)
if new_word:
if new_word in self.verb_p2f_map:
stem = new_word + "&" + self.verb_p2f_map[new_word]
return stem
if word_pos is None or word_pos == "N":
# پسوندهای مالکیت
stem_candidate = word
candidate_list = self.remove_postfixes(word, ["م", "ت", "ش", "یم", "یت", "یش",
"یتان", "یشان", "یمان",
"مان", "تان", "شان", "ان"])
if len(candidate_list) > 0:
stem_candidate = self.select_candidate(candidate_list, self.noun_lexicon)
if stem_candidate:
new_word = stem_candidate
else:
new_word = self.select_candidate(candidate_list)
stem_candidate = new_word
else:
new_word = stem_candidate
if new_word in self.noun_lexicon:
return self.map_irregular_noun(new_word)
candidate_list = self.remove_postfixes(new_word, ["ها", "ات", "های",
"ان", "هایی", "ین"])
if len(candidate_list) > 0:
stem_candidate = self.select_candidate(candidate_list, self.noun_lexicon)
if stem_candidate:
new_word = stem_candidate
else:
new_word = self.select_candidate(candidate_list)
stem_candidate = new_word
else:
new_word = stem_candidate
if new_word in self.noun_lexicon:
return self.map_irregular_noun(new_word)
candidate_list = self.remove_postfixes(new_word, ["گ"])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
new_word = new_word + "ه"
stem_candidate = new_word
else:
new_word = stem_candidate
if new_word in self.noun_lexicon:
return self.map_irregular_noun(new_word)
candidate_list = self.remove_postfixes(new_word, self.postfix_list)
if len(candidate_list) > 0:
stem_candidate = self.select_candidate(candidate_list, self.noun_lexicon)
if stem_candidate:
new_word = stem_candidate
else:
new_word = self.select_candidate(candidate_list)
stem_candidate = new_word
else:
new_word = stem_candidate
if new_word in self.noun_lexicon:
return self.map_irregular_noun(new_word)
# stem = new_word
candidate_list = self.remove_prefixes(new_word, self.prefix_list)
if len(candidate_list) > 0:
stem_candidate = self.select_candidate(candidate_list, self.noun_lexicon)
if stem_candidate:
new_word = stem_candidate
else:
new_word = self.select_candidate(candidate_list)
stem_candidate = new_word
else:
new_word = stem_candidate
if new_word in self.noun_lexicon:
return self.map_irregular_noun(new_word)
# stem = new_word
# افعال پیشوندی
candidate_list = self.remove_prefixes(word, ['در', 'بر', 'پر', 'باز',
'ور', 'فرو', 'فرا', 'وا'])
if len(candidate_list) > 0:
new_word = self.select_candidate(candidate_list)
if new_word:
tmp_pr = word[:-len(new_word)].strip().strip('\u200c')
new_word = self.convert_to_stem(new_word, word_pos='V')
if new_word and new_word in self.verb_lexicon:
return tmp_pr + new_word
return word
|