explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add conversion rule for .conll

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-17 13:13:48 +02:00
parent 692bd2a186
commit 55dab77de8
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/cli/convert.py
View File

@ -12,7 +12,8 @@ from ..util import prints
# from /converters. # from /converters.
CONVERTERS = { CONVERTERS = {
'.conllu': conllu2json '.conllu': conllu2json,
'.conll': conllu2json
} }

5
spacy/cli/converters/conllu2json.py
View File

@ -28,6 +28,7 @@ def conllu2json(input_path, output_path, n_sents=10, use_morphology=False):
sentences = [] sentences = []
output_filename = input_path.parts[-1].replace(".conllu", ".json") output_filename = input_path.parts[-1].replace(".conllu", ".json")
output_filename = input_path.parts[-1].replace(".conll", ".json")
output_file = output_path / output_filename output_file = output_path / output_filename
with output_file.open('w', encoding='utf-8') as f: with output_file.open('w', encoding='utf-8') as f:
f.write(json_dumps(docs)) f.write(json_dumps(docs))
@ -46,8 +47,8 @@ def read_conllx(input_path, use_morphology=False, n=0):
tokens = [] tokens = []
for line in lines: for line in lines:
id_, word, lemma, pos, tag, morph, head, dep, _1, \ parts = line.split('\t')
_2 = line.split('\t') id_, word, lemma, pos, tag, morph, head, dep, _1, _2 = parts
if '-' in id_ or '.' in id_: if '-' in id_ or '.' in id_:
continue continue
try: try: