kleister-nda/run.py

54 lines
1.7 KiB
Python
Raw Normal View History

2022-05-03 20:59:50 +02:00
#!/usr/bin/env python
# coding: utf-8
# In[36]:
import re
# In[4]:
states = ["Alaska", "Alabama", "Arkansas", "American Samoa", "Arizona", "California", "Colorado", "Connecticut", "District ", "of Columbia", "Delaware", "Florida", "Georgia", "Guam", "Hawaii", "Iowa", "Idaho", "Illinois", "Indiana", "Kansas", "Kentucky", "Louisiana", "Massachusetts", "Maryland", "Maine", "Michigan", "Minnesota", "Missouri", "Mississippi", "Montana", "North Carolina", "North Dakota", "Nebraska", "New Hampshire", "New Jersey", "New Mexico", "Nevada", "New York", "Ohio", "Oklahoma", "Oregon", "Pennsylvania", "Puerto Rico", "Rhode Island", "South Carolina", "South Dakota", "Tennessee", "Texas", "Utah", "Virginia", "Virgin Islands", "Vermont", "Washington", "Wisconsin", "West Virginia", "Wyoming"]
# In[23]:
rgx = re.compile(r'\b(' + '|'.join(states) + r')\b')
# In[41]:
def nda(path_in, path_out):
results = []
with open(path_in, 'r', encoding='utf-8') as file:
#removeAccents(path_in)
for line in file.readlines():
line = line.replace('.', ' ').replace(',', ' ').lower()
words = line.split()
jur = rgx.search(line)
if jur:
results.append('jurisdiction=' + jur.group().replace(' ', '_'))
#else:
# results.append('\n')
date = re.findall(r'(\d+-\d+-\d+)',line)
if date:
results.append('effective_date=' + jur.group().replace(' ', '_'))
results.append('\n')
with open(path_out, 'w') as file:
for r in results:
file.write(r + '\n')
# In[ ]:
#pliki
nda('dev-0/in.tsv', 'dev-0/out.tsv')
nda('train/in.tsv', 'train/out.tsv')
nda('test-A/in.tsv', 'test-A/out.tsv')