blob: c6da5e9dfe8ce3db292d6d685317313a9c98136c (
plain)
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
|
#!/usr/bin/env python
import sys
import os
import argparse
import logging
import configobj
import cdec.sa
def main():
logging.basicConfig(level=logging.INFO)
parser = argparse.ArgumentParser(description='Extract grammars from a compiled corpus.')
parser.add_argument('-c', '--config', required=True,
help='Extractor configuration')
parser.add_argument('-g', '--grammars', required=True,
help='Grammar output path')
args = parser.parse_args()
if not os.path.exists(args.grammars):
os.mkdir(args.grammars)
extractor = cdec.sa.GrammarExtractor(configobj.ConfigObj(args.config, unrepr=True))
for i, sentence in enumerate(sys.stdin):
sentence = sentence[:-1]
grammar_file = os.path.join(args.grammars, 'grammar.{0}'.format(i))
with open(grammar_file, 'w') as output:
for rule in extractor.grammar(sentence):
output.write(str(rule)+'\n')
grammar_file = os.path.abspath(grammar_file)
print('<seg grammar="{0}">{1}</seg>'.format(grammar_file, sentence))
if __name__ == '__main__':
main()
|
