Spaces:
Runtime error
Runtime error
File size: 9,102 Bytes
e50fe35 |
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 |
import argparse
import sys
from indicnlp import loader
from indicnlp.tokenize import indic_tokenize
from indicnlp.tokenize import indic_detokenize
from indicnlp.normalize import indic_normalize
from indicnlp.morph import unsupervised_morph
from indicnlp.tokenize import sentence_tokenize
from indicnlp.syllable import syllabifier
from indicnlp.transliterate import unicode_transliterate
from indicnlp.transliterate import script_unifier
DEFAULT_ENCODING='utf-8'
def run_detokenize(args):
for line in args.infile:
args.outfile.write(indic_detokenize.trivial_detokenize(line,args.lang))
def run_tokenize(args):
for line in args.infile:
args.outfile.write(' '.join(
indic_tokenize.trivial_tokenize(line,args.lang)))
def run_sentence_split(args):
text=' '.join([ l.replace('\n','').replace('\r','') for l in args.infile])
outlines=sentence_tokenize.sentence_split(text,args.lang)
for line in outlines:
args.outfile.write(line+'\n')
def run_normalize(args):
# TODO: add more options to cli
remove_nuktas=False
normalize_nasals='do_nothing'
# create normalizer
factory=indic_normalize.IndicNormalizerFactory()
normalizer=factory.get_normalizer(args.lang,
remove_nuktas=remove_nuktas,
nasals_mode=normalize_nasals)
# DO normalization
for line in args.infile:
normalized_line=normalizer.normalize(line)
args.outfile.write(normalized_line)
def run_morph(args):
add_marker=False
analyzer=unsupervised_morph.UnsupervisedMorphAnalyzer(args.lang,add_marker)
for line in args.infile:
morph_tokens=analyzer.morph_analyze_document(line.strip().split(' '))
args.outfile.write(' '.join(morph_tokens) + '\n')
def run_syllabify(args):
for line in args.infile:
new_line = ' '.join(
[ ' '.join(syllabifier.orthographic_syllabify(w,args.lang))
for w in line.strip().split(' ') ]
)
args.outfile.write(new_line+'\n')
def run_wc(args):
# if args.l==False and args.w==False and args.c==False:
# args.l, args.w, args.c= True, True, True
nl=0
nw=0
nc=0
for line in args.infile:
nl+=1
nw+=len(line.strip(' ').split(' '))
nc+=len(line)
print('{} {} {}'.format(nl,nw,nc))
def run_indic2roman(args):
for line in args.infile:
transliterated_line=unicode_transliterate.ItransTransliterator.to_itrans(
line,args.lang)
args.outfile.write(transliterated_line)
def run_roman2indic(args):
for line in args.infile:
transliterated_line=unicode_transliterate.ItransTransliterator.from_itrans(
line,args.lang)
args.outfile.write(transliterated_line)
def run_script_unify(args):
unifier=None
if args.mode=='aggressive':
unifier=script_unifier.AggressiveScriptUnifier(nasals_mode='to_anusvaara_relaxed', common_lang=args.common_lang)
elif args.mode=='basic':
unifier=script_unifier.BasicScriptUnifier(nasals_mode='do_nothing',
common_lang=args.common_lang)
elif args.mode=='naive':
unifier=script_unifier.NaiveScriptUnifier(common_lang=args.common_lang)
assert(unifier is not None)
for line in args.infile:
transliterated_line=unifier.transform(line,args.lang)
args.outfile.write(transliterated_line)
def run_script_convert(args):
for line in args.infile:
transliterated_line=unicode_transliterate.UnicodeIndicTransliterator.transliterate(
line,args.srclang,args.tgtlang)
args.outfile.write(transliterated_line)
def add_common_monolingual_args(task_parser):
task_parser.add_argument('infile',
type=argparse.FileType('r',encoding=DEFAULT_ENCODING),
nargs='?',
default=sys.stdin,
help='Input File path',
)
task_parser.add_argument('outfile',
type=argparse.FileType('w',encoding=DEFAULT_ENCODING),
nargs='?',
default=sys.stdout,
help='Output File path',
)
task_parser.add_argument('-l', '--lang',
help='Language',
)
def add_common_bilingual_args(task_parser):
task_parser.add_argument('infile',
type=argparse.FileType('r',encoding=DEFAULT_ENCODING),
nargs='?',
default=sys.stdin,
help='Input File path',
)
task_parser.add_argument('outfile',
type=argparse.FileType('w',encoding=DEFAULT_ENCODING),
nargs='?',
default=sys.stdout,
help='Output File path',
)
task_parser.add_argument('-s', '--srclang',
help='Source Language',
)
task_parser.add_argument('-t', '--tgtlang',
help='Target Language',
)
def add_tokenize_parser(subparsers):
task_parser=subparsers.add_parser('tokenize',
help='tokenizer help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_tokenize)
def add_detokenize_parser(subparsers):
task_parser=subparsers.add_parser('detokenize',
help='de-tokenizer help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_detokenize)
def add_sentence_split_parser(subparsers):
task_parser=subparsers.add_parser('sentence_split', help='sentence split help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_sentence_split)
def add_normalize_parser(subparsers):
task_parser=subparsers.add_parser('normalize', help='normalizer help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_normalize)
def add_morph_parser(subparsers):
task_parser=subparsers.add_parser('morph', help='morph help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_morph)
def add_syllabify_parser(subparsers):
task_parser=subparsers.add_parser('syllabify', help='syllabify help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_syllabify)
def add_wc_parser(subparsers):
task_parser=subparsers.add_parser('wc', help='wc help')
task_parser.add_argument('infile',
type=argparse.FileType('r',encoding=DEFAULT_ENCODING),
nargs='?',
default=sys.stdin,
help='Input File path',
)
# task_parser.add_argument('-l', action='store_true')
# task_parser.add_argument('-w', action='store_true')
# task_parser.add_argument('-c', action='store_true')
# task_parser.set_defaults(l=False)
# task_parser.set_defaults(w=False)
# task_parser.set_defaults(c=False)
task_parser.set_defaults(func=run_wc)
def add_indic2roman_parser(subparsers):
task_parser=subparsers.add_parser('indic2roman', help='indic2roman help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_indic2roman)
def add_roman2indic_parser(subparsers):
task_parser=subparsers.add_parser('roman2indic', help='roman2indic help')
add_common_monolingual_args(task_parser)
task_parser.set_defaults(func=run_indic2roman)
def add_script_unify_parser(subparsers):
task_parser=subparsers.add_parser('script_unify', help='script_unify help')
add_common_monolingual_args(task_parser)
task_parser.add_argument('-m','--mode',
default='basic',
choices=['naive', 'basic', 'aggressive'] ,
help='Script unification mode',
)
task_parser.add_argument('-c','--common_lang',
default='hi',
help='Common language in which all languages are represented',
)
task_parser.set_defaults(func=run_script_unify)
def add_script_convert_parser(subparsers):
task_parser=subparsers.add_parser('script_convert', help='script convert help')
add_common_bilingual_args(task_parser)
task_parser.set_defaults(func=run_script_convert)
def get_parser():
parser = argparse.ArgumentParser(prog='indicnlp')
subparsers = parser.add_subparsers(help='Invoke each operation with one of the subcommands', dest='subcommand')
add_tokenize_parser(subparsers)
add_detokenize_parser(subparsers)
add_sentence_split_parser(subparsers)
add_normalize_parser(subparsers)
add_morph_parser(subparsers)
add_syllabify_parser(subparsers)
add_wc_parser(subparsers)
add_indic2roman_parser(subparsers)
add_roman2indic_parser(subparsers)
add_script_unify_parser(subparsers)
add_script_convert_parser(subparsers)
return parser
def main():
parser=get_parser()
args=parser.parse_args()
# print(args)
args.func(args)
if __name__ == '__main__':
loader.load()
main()
|