File size: 8,461 Bytes
2c8dc05 |
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 |
# import sys, os
# SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
# sys.path.append(SCRIPT_DIR)
# combined lexical analyzer and parser
from Unified_parser.ply.lex import Lexer
from Unified_parser.ply.yacc import yacc
from Unified_parser.globals import *
from Unified_parser.helpers import *
import sys
from sys import exit
from Unified_parser.get_phone_mapped_python import *
# tokens used
tokens = ('kaki_c', 'conjsyll2_c', 'fullvowel_b', 'kaki_a', 'kaki_b', 'conjsyll2_b', 'conjsyll2_a',
'conjsyll1', 'nukchan_b','nukchan_a', 'yarule', 'fullvowel_a', 'vowel')
# parser part
def p_sentence(p):
'''
sentence : words
'''
if p.parser.g.flags.parseLevel == 0:
p.parser.g.words.syllabifiedWordOut = p[1]
if p.parser.g.words.syllabifiedWordOut.find('&&') != -1:
p.parser.g.words.syllabifiedWordOut = rec_replace(p.parser.g.words.syllabifiedWordOut,'&&','&')
p.parser.g.flags.parseLevel += 1
else:
p.parser.g.words.phonifiedWord = p[1]
def p_words_syltoken(p):
'''
words : syltoken
'''
if(p.parser.g.flags.DEBUG):
print(f"Syll:\t{p[1]}")
p[0] = p[1]
def p_words_wordsandsyltoken(p):
'''
words : words syltoken
'''
if(p.parser.g.flags.DEBUG):
print(f"Syll:\t{p[2]}")
p[0] = p[1] + p[2]
def p_syltoken(p):
'''
syltoken : fullvowel_b
| fullvowel_a
| conjsyll2_c
| conjsyll2_b
| conjsyll2_a
| conjsyll1
| nukchan_b
| nukchan_a
| yarule
| vowel
'''
p[0] = p[1]
def p_syltoken1(p):
'''
syltoken :
| kaki_c
| kaki_a
| kaki_b
'''
if (p.parser.g.flags.DEBUG):
print(f'kaki : {p[1]}')
p[0] = p[1]
def p_error(p):
print('parse error')
exit(1)
# print the help of syntax
def printHelp():
print("UnifiedParser - Usage Instructions")
print("Run python3 parser.py wd lsflag wfflag clearflag")
print("wd - word to parse in unicode.")
print("lsflag - always 0. we are not using this.")
print("wfflag - 0 for Monophone parsing, 1 for syllable parsing, 2 for Akshara Parsing")
print("clearflag -0. for normal syntx, 1 for removing the lisp like format of output and to just produce space separated output. 2 for cls labled output")
print("language - name of language in quationes")
def wordparse(wd : str, lsflag : int, wfflag : int, clearflag : int,language_main :str):
g = GLOBALS()
lexer = Lexer()
parser = yacc()
parser.g = g
g.flags.DEBUG = False
wd = wd.strip(' ') # hidden characters
if lsflag not in [0,1] or wfflag not in [0,1,2]:
print("Invalid input")
exit(1)
g.flags.LangSpecificCorrectionFlag = lsflag
g.flags.writeFormat = wfflag
if wfflag == 4:
g.flags.writeFormat = 1
g.flags.syllTagFlag = 1
word = wd
if g.flags.DEBUG:
print(f'Word : {word}')
word = RemoveUnwanted(word)
if g.flags.DEBUG:
print(f'Cleared Word : {word}')
if SetlanguageFeat(g, word) == 0:
return 0
if CheckDictionary(g, word) != 0:
return 0
if g.flags.DEBUG:
print(f'langId : {g.langId}')
word = ConvertToSymbols(g, word)
if g.flags.DEBUG:
print(f"Symbols code : {g.words.unicodeWord}")
print(f"Symbols syllables : {g.words.syllabifiedWord}")
language_main=language_main.lower()
# if language_main == "telugu":
# g.currLang = g.TELUGU
# g.langId = 3
# if(g.langId < 5):
# g.isSouth = 1
# print("language:",language_main)
# if language_main == "marathi":
# print("inside main")
# g.currLang = g.KANNADA
# g.langId = 4
# if(g.langId < 5):
# g.isSouth = 1
# print("language:",language_main)
parser.parse(g.words.syllabifiedWord, lexer=lexer)
if(g.flags.DEBUG):
print(f"Syllabified Word : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = rec_replace(g.words.syllabifiedWordOut, '&#&','&') + '&'
if(g.flags.DEBUG):
print(f"Syllabified Word out : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = LangSpecificCorrection(g, g.words.syllabifiedWordOut, g.flags.LangSpecificCorrectionFlag)
if(g.flags.DEBUG):
print(f"Syllabified Word langCorr : {g.words.syllabifiedWordOut}")
# if(g.flags.DEBUG):
# print(f"Syllabified Word gemCorr : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = CleanseWord(g.words.syllabifiedWordOut)
if(g.flags.DEBUG):
print(f"Syllabified Word memCorr : {g.words.syllabifiedWordOut}")
if not g.isSouth:
if g.flags.DEBUG:
print('NOT SOUTH')
count = 0
for i in range(len(g.words.syllabifiedWordOut)):
if g.words.syllabifiedWordOut[i] == '&':
count += 1
splitPosition = 2
if GetPhoneType(g, g.words.syllabifiedWordOut, 1) == 1:
if count > 2:
tpe = GetPhoneType(g, g.words.syllabifiedWordOut, 2)
if tpe == 2:
splitPosition = 1
elif tpe == 3:
splitPosition = 3
else:
splitPosition = 1
count = 0
for i in range(len(g.words.syllabifiedWordOut)):
if g.words.syllabifiedWordOut[i] == '&':
count += 1
if count > splitPosition:
count = i
break
start, end = g.words.syllabifiedWordOut, g.words.syllabifiedWordOut
end = end[count:]
start = start[:count]
if(g.flags.DEBUG):
print(f"posi {count} {start} {end}")
end = SchwaSpecificCorrection(g, end)
if(g.flags.DEBUG):
print(f"prefinal : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = start + end
if(g.flags.DEBUG):
print(f"prefinal1 : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = CleanseWord(g.words.syllabifiedWordOut)
if(g.flags.DEBUG):
print(f"final : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = SchwaDoubleConsonent(g.words.syllabifiedWordOut)
if(g.flags.DEBUG):
print(f"final0 : {g.words.syllabifiedWordOut}")
g.words.syllabifiedWordOut = GeminateCorrection(g.words.syllabifiedWordOut, 0)
g.words.syllabifiedWordOut = MiddleVowel(g, g.words.syllabifiedWordOut)
g.words.syllabifiedWordOut = Syllabilfy(g.words.syllabifiedWordOut)
SplitSyllables(g,g.words.syllabifiedWordOut)
temp_list=g.syllableList
if g.flags.DEBUG:
print("temp_list_1",temp_list)
# print("temp_list_1",temp_list)
# for i in range(len(temp_list)):
# print("output_a", temp_list[i] )
# temp_list[i]=convert_to_main_lang (g,temp_list[i], language_main)
# print("output_b", temp_list[i] )
WritetoFiles(g)
if clearflag == 0:
return g.answer
if clearflag == 1:
t = g.words.outputText
t = t.split('"')
ln = len(t)
i = 1
g.answer = ''
while i < ln:
g.answer += t[i] + ' '
i += 2
g.answer.strip()
return g.answer
if clearflag == 2:
t = g.words.outputText
t = t.split('"')
# print(t)
ln = len(t)
i = 1
g.answer = ''
text_replacer=TextReplacer()
while i < ln:
if len(t[i])>1 and ord(t[i][0])<128 and ord(t[i][0])>=65:
temp = text_replacer.apply_replacements_by_phonems(t[i])
g.answer += temp
elif len(t[i])==1 and ord(t[i][0])<128 and ord(t[i][0])>=65:
g.answer += t[i]
i += 1
g.answer.strip()
return g.answer
def safe_word_parse(wd : str, lsflag : int, wfflag : int, clearflag : int,language : str):
try:
ans = wordparse(wd, lsflag, wfflag, clearflag,language)
# print(ans)
except:
print(f'failed on {wd}')
ans = 'FAILED'
return wd, ans,
if __name__ == '__main__':
if (len(sys.argv) != 6):
printHelp()
exit(-1)
ans = wordparse(sys.argv[1], int(sys.argv[2]), int(sys.argv[3]), int(sys.argv[4]),str(sys.argv[5]))
print(ans)
|