mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
37c7c85a86
* Support nowrap setting in util.prints * Tidy up and fix whitespace * Simplify script and use read_jsonl helper * Add JSON schemas (see #2928) * Deprecate Doc.print_tree Will be replaced with Doc.to_json, which will produce a unified format * Add Doc.to_json() method (see #2928) Converts Doc objects to JSON using the same unified format as the training data. Method also supports serializing selected custom attributes in the doc._. space. * Remove outdated test * Add write_json and write_jsonl helpers * WIP: Update spacy train * Tidy up spacy train * WIP: Use wasabi for formatting * Add GoldParse helpers for JSON format * WIP: add debug-data command * Fix typo * Add missing import * Update wasabi pin * Add missing import * 💫 Refactor CLI (#2943) To be merged into #2932. ## Description - [x] refactor CLI To use [`wasabi`](https://github.com/ines/wasabi) - [x] use [`black`](https://github.com/ambv/black) for auto-formatting - [x] add `flake8` config - [x] move all messy UD-related scripts to `cli.ud` - [x] make converters function that take the opened file and return the converted data (instead of having them handle the IO) ### Types of change enhancement ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. * Update wasabi pin * Delete old test * Update errors * Fix typo * Tidy up and format remaining code * Fix formatting * Improve formatting of messages * Auto-format remaining code * Add tok2vec stuff to spacy.train * Fix typo * Update wasabi pin * Fix path checks for when train() is called as function * Reformat and tidy up pretrain script * Update argument annotations * Raise error if model language doesn't match lang * Document new train command
66 lines
2.1 KiB
Python
66 lines
2.1 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.cli.schemas import get_schema, validate_json
|
|
from spacy.tokens import Doc
|
|
from ..util import get_doc
|
|
|
|
|
|
@pytest.fixture()
|
|
def doc(en_vocab):
|
|
words = ["c", "d", "e"]
|
|
pos = ["VERB", "NOUN", "NOUN"]
|
|
tags = ["VBP", "NN", "NN"]
|
|
heads = [0, -1, -2]
|
|
deps = ["ROOT", "dobj", "dobj"]
|
|
ents = [(1, 2, "ORG")]
|
|
return get_doc(
|
|
en_vocab, words=words, pos=pos, tags=tags, heads=heads, deps=deps, ents=ents
|
|
)
|
|
|
|
|
|
def test_doc_to_json(doc):
|
|
json_doc = doc.to_json()
|
|
assert json_doc["text"] == "c d e "
|
|
assert len(json_doc["tokens"]) == 3
|
|
assert json_doc["tokens"][0]["pos"] == "VERB"
|
|
assert json_doc["tokens"][0]["tag"] == "VBP"
|
|
assert json_doc["tokens"][0]["dep"] == "ROOT"
|
|
assert len(json_doc["ents"]) == 1
|
|
assert json_doc["ents"][0]["start"] == 2 # character offset!
|
|
assert json_doc["ents"][0]["end"] == 3 # character offset!
|
|
assert json_doc["ents"][0]["label"] == "ORG"
|
|
|
|
|
|
def test_doc_to_json_underscore(doc):
|
|
Doc.set_extension("json_test1", default=False)
|
|
Doc.set_extension("json_test2", default=False)
|
|
doc._.json_test1 = "hello world"
|
|
doc._.json_test2 = [1, 2, 3]
|
|
json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
|
|
assert "_" in json_doc
|
|
assert json_doc["_"]["json_test1"] == "hello world"
|
|
assert json_doc["_"]["json_test2"] == [1, 2, 3]
|
|
|
|
|
|
def test_doc_to_json_underscore_error_attr(doc):
|
|
"""Test that Doc.to_json() raises an error if a custom attribute doesn't
|
|
exist in the ._ space."""
|
|
with pytest.raises(ValueError):
|
|
doc.to_json(underscore=["json_test3"])
|
|
|
|
|
|
def test_doc_to_json_underscore_error_serialize(doc):
|
|
"""Test that Doc.to_json() raises an error if a custom attribute value
|
|
isn't JSON-serializable."""
|
|
Doc.set_extension("json_test4", method=lambda doc: doc.text)
|
|
with pytest.raises(ValueError):
|
|
doc.to_json(underscore=["json_test4"])
|
|
|
|
|
|
def test_doc_to_json_valid_training(doc):
|
|
json_doc = doc.to_json()
|
|
errors = validate_json([json_doc], get_schema("training"))
|
|
assert not errors
|