mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
a5cd203284
* Reduce stored lexemes data, move feats to lookups
* Move non-derivable lexemes features (`norm / cluster / prob`) to
`spacy-lookups-data` as lookups
* Get/set `norm` in both lookups and `LexemeC`, serialize in lookups
* Remove `cluster` and `prob` from `LexemesC`, get/set/serialize in
lookups only
* Remove serialization of lexemes data as `vocab/lexemes.bin`
* Remove `SerializedLexemeC`
* Remove `Lexeme.to_bytes/from_bytes`
* Modify normalization exception loading:
* Always create `Vocab.lookups` table `lexeme_norm` for
normalization exceptions
* Load base exceptions from `lang.norm_exceptions`, but load
language-specific exceptions from lookups
* Set `lex_attr_getter[NORM]` including new lookups table in
`BaseDefaults.create_vocab()` and when deserializing `Vocab`
* Remove all cached lexemes when deserializing vocab to override
existing normalizations with the new normalizations (as a replacement
for the previous step that replaced all lexemes data with the
deserialized data)
* Skip English normalization test
Skip English normalization test because the data is now in
`spacy-lookups-data`.
* Remove norm exceptions
Moved to spacy-lookups-data.
* Move norm exceptions test to spacy-lookups-data
* Load extra lookups from spacy-lookups-data lazily
Load extra lookups (currently for cluster and prob) lazily from the
entry point `lg_extra` as `Vocab.lookups_extra`.
* Skip creating lexeme cache on load
To improve model loading times, do not create the full lexeme cache when
loading. The lexemes will be created on demand when processing.
* Identify numeric values in Lexeme.set_attrs()
With the removal of a special case for `PROB`, also identify `float` to
avoid trying to convert it with the `StringStore`.
* Skip lexeme cache init in from_bytes
* Unskip and update lookups tests for python3.6+
* Update vocab pickle to include lookups_extra
* Update vocab serialization tests
Check strings rather than lexemes since lexemes aren't initialized
automatically, account for addition of "_SP".
* Re-skip lookups test because of python3.5
* Skip PROB/float values in Lexeme.set_attrs
* Convert is_oov from lexeme flag to lex in vectors
Instead of storing `is_oov` as a lexeme flag, `is_oov` reports whether
the lexeme has a vector.
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
63 lines
1.8 KiB
Python
63 lines
1.8 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["ca.", "m.a.o.", "Jan.", "Dec.", "kr.", "jf."])
|
|
def test_da_tokenizer_handles_abbr(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["Jul.", "jul.", "Tor.", "Tors."])
|
|
def test_da_tokenizer_handles_ambiguous_abbr(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["1.", "10.", "31."])
|
|
def test_da_tokenizer_handles_dates(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
|
|
|
|
def test_da_tokenizer_handles_exc_in_text(da_tokenizer):
|
|
text = "Det er bl.a. ikke meningen"
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 5
|
|
assert tokens[2].text == "bl.a."
|
|
|
|
|
|
def test_da_tokenizer_handles_custom_base_exc(da_tokenizer):
|
|
text = "Her er noget du kan kigge i."
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 8
|
|
assert tokens[6].text == "i"
|
|
assert tokens[7].text == "."
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,n_tokens",
|
|
[
|
|
("Godt og/eller skidt", 3),
|
|
("Kør 4 km/t på vejen", 5),
|
|
("Det blæser 12 m/s.", 5),
|
|
("Det blæser 12 m/sek. på havnen", 6),
|
|
("Windows 8/Windows 10", 5),
|
|
("Billeten virker til bus/tog/metro", 8),
|
|
("26/02/2019", 1),
|
|
("Kristiansen c/o Madsen", 3),
|
|
("Sprogteknologi a/s", 2),
|
|
("De boede i A/B Bellevue", 5),
|
|
# note: skipping due to weirdness in UD_Danish-DDT
|
|
# ("Rotorhastigheden er 3400 o/m.", 5),
|
|
("Jeg købte billet t/r.", 5),
|
|
("Murerarbejdsmand m/k søges", 3),
|
|
("Netværket kører over TCP/IP", 4),
|
|
],
|
|
)
|
|
def test_da_tokenizer_slash(da_tokenizer, text, n_tokens):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == n_tokens
|