spaCy/spacy/cli/convert.py

48 lines
1.7 KiB
Python
Raw Normal View History

2017-04-07 14:04:17 +03:00
# coding: utf8
2017-04-13 14:51:54 +03:00
from __future__ import unicode_literals
2017-04-07 14:04:17 +03:00
import plac
2017-04-13 14:51:54 +03:00
from pathlib import Path
2017-04-07 14:04:17 +03:00
from .converters import conllu2json, conllubio2json, iob2json, conll_ner2json
from ._messages import Messages
2017-05-08 00:25:29 +03:00
from ..util import prints
2017-04-07 14:04:17 +03:00
2017-10-27 15:38:39 +03:00
# Converters are matched by file extension. To add a converter, add a new
# entry to this dict with the file extension mapped to the converter function
# imported from /converters.
2017-04-07 14:04:17 +03:00
CONVERTERS = {
'conllubio': conllubio2json,
2017-10-10 04:06:28 +03:00
'conllu': conllu2json,
'conll': conllu2json,
'ner': conll_ner2json,
'iob': iob2json,
2017-04-07 14:04:17 +03:00
}
@plac.annotations(
input_file=("input file", "positional", None, str),
output_dir=("output directory for converted file", "positional", None, str),
2017-08-18 23:26:12 +03:00
n_sents=("Number of sentences per doc", "option", "n", int),
2017-10-10 04:06:28 +03:00
converter=("Name of converter (auto, iob, conllu or ner)", "option", "c", str),
2017-10-27 15:38:39 +03:00
morphology=("Enable appending morphology to tags", "flag", "m", bool))
def convert(input_file, output_dir, n_sents=1, morphology=False, converter='auto'):
"""
Convert files into JSON format for use with train command and other
experiment management functions.
"""
2017-04-07 14:04:17 +03:00
input_path = Path(input_file)
output_path = Path(output_dir)
2017-05-08 00:25:29 +03:00
if not input_path.exists():
prints(input_path, title=Messages.M028, exits=1)
2017-04-07 14:04:17 +03:00
if not output_path.exists():
prints(output_path, title=Messages.M029, exits=1)
2017-10-10 04:06:28 +03:00
if converter == 'auto':
converter = input_path.suffix[1:]
2017-10-27 15:38:39 +03:00
if converter not in CONVERTERS:
prints(Messages.M031.format(converter=converter),
title=Messages.M030, exits=1)
2017-10-10 04:06:28 +03:00
func = CONVERTERS[converter]
func(input_path, output_path,
n_sents=n_sents, use_morphology=morphology)