if 'Title' in doc.fields:
outs.write(u"%%#Field\tTitle\n")
write_text(doc.fields['Title'], outs)
outs.write(u"%%#Field\tBody\n")
write_text(doc.fields['Body'], outs)
def write_text(text, outs):
for token in text:
outs.write(u"\t".join(token))
outs.write("\n")
if __name__ == '__main__':
import sys
try:
params, args = cmd_utils.get_params_sing(sys.argv[1:], 'i:o:m:ta', 'i', 0)
if not os.path.isdir(params['i']):
raise ValueError('Input must be a directory of files.')
except ValueError as err:
print('Error: {0}'.format(err))
print(('Usage: {0} -i input_dir [-o output_file] -m [hunpos_model] ' +
'[-a]').format(sys.argv[0]))
print(' input_dir: the directory with the input text files.')
print(' hunpos_model: the hunpos model file.')
print(' output_file: the conll2 output file. If omitted, the result will')
print(' be written to stdout.')
print(' hunpos_model: the hunpos model file.')
print(' -a: the output is appended to output_file, instead of overwriting it.')
sys.exit()
if 'o' in params:
if 'Body' in doc.fields:
outs.write(u"%%#Field\tBody\n")
write_text(doc.fields['Body'], outs)
def write_text(text, outs):
for token in text:
outs.write(u"\t".join(token))
outs.write("\n")
if __name__ == '__main__':
import sys
try:
params, args = cmd_utils.get_params_sing(sys.argv[1:], 'i:o:m:ta', 'i',
0)
if not os.path.isdir(params['i']):
raise ValueError('Input must be a directory of files.')
except ValueError as err:
print('Error: {0}'.format(err))
print(('Usage: {0} -i input_dir [-o output_file] -m [hunpos_model] ' +
'[-t] [-a]').format(sys.argv[0]))
print(' input_dir: the directory with the input text files.')
print(' hunpos_model: the hunpos model file.')
print(
' output_file: the conll2 output file. If omitted, the result will'
)
print(' be written to stdout.')
print(' hunpos_model: the hunpos model file.')
print(
' -t: If specified, the first non-empty line of the the text files are'
for mapping in mappings:
try:
key, value = mapping.strip().split("\t")
type_map[key] = value
except (ValueError):
continue
return type_map
def print_usage_and_exit():
sys.stderr.write('Usage: {0} dbpedia_type_file [-c classes_OWL_file] [-m NE_mappings]\n'.format(__file__))
sys.exit()
if __name__ == '__main__':
import sys
try:
params, args = get_params_sing(sys.argv[1:], 'c:m:k', '', 1)
except ValueError as ve:
sys.stderr.write(ve + "\n")
print_usage_and_exit()
if len(args) != 1:
print_usage_and_exit()
# with open(sys.argv[1], 'r', encoding = 'utf-8') as type_stream:
with FileReader(args[0], encoding='utf-8').open() as type_stream:
lines = merge_pairs(extract_dbpedia_type(type_stream))
filter = __read_map(params['m']) if 'm' in params else None
if 'c' in params:
lines = filter_general(lines, OwlClassHierarchy(params['c']), filter)
if 'm' in params:
lines = filter_type(lines, filter, 'k' in params)