mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
ffdd5e964f
* Add todo * Auto-format * Update wasabi pin * Format training results with wasabi * Remove loading animation from model saving Currently behaves weirdly * Inline messages * Remove unnecessary path2str Already taken care of by printer * Inline messages in CLI * Remove unused function * Move loading indicator into loading function * Check for invalid whitespace entities
21 lines
671 B
Python
21 lines
671 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import srsly
|
|
|
|
from ...util import get_lang_class
|
|
|
|
|
|
def ner_jsonl2json(input_data, lang=None, n_sents=10, use_morphology=False):
|
|
if lang is None:
|
|
raise ValueError("No --lang specified, but tokenization required")
|
|
json_docs = []
|
|
input_tuples = [srsly.json_loads(line) for line in input_data]
|
|
nlp = get_lang_class(lang)()
|
|
for i, (raw_text, ents) in enumerate(input_tuples):
|
|
doc = nlp.make_doc(raw_text)
|
|
doc[0].is_sent_start = True
|
|
doc.ents = [doc.char_span(s, e, label=L) for s, e, L in ents["entities"]]
|
|
json_docs.append(doc.to_json())
|
|
return json_docs
|