explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' of https://github.com/explosion/spaCy into develop

Browse Source
This commit is contained in:
Matthew Honnibal 2019-03-11 15:59:28 +01:00
commit e2b9b523ce
18 changed files with 614 additions and 561 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
spacy/lang/fa/__init__.py
View File

@ -27,6 +27,7 @@ class PersianDefaults(Language.Defaults):
stop_words = STOP_WORDS
tag_map = TAG_MAP
suffixes = TOKENIZER_SUFFIXES
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
class Persian(Language):

2
spacy/lang/he/__init__.py
View File

@ -14,7 +14,7 @@ class HebrewDefaults(Language.Defaults):
lex_attr_getters[LANG] = lambda text: "he"
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = STOP_WORDS
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
class Hebrew(Language):
lang = "he"

1
spacy/lang/ja/__init__.py
View File

@ -94,6 +94,7 @@ class JapaneseDefaults(Language.Defaults):
lex_attr_getters[LANG] = lambda _text: "ja"
stop_words = STOP_WORDS
tag_map = TAG_MAP
writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
@classmethod
def create_tokenizer(cls, nlp=None):

2
spacy/lang/zh/__init__.py
View File

@ -14,7 +14,7 @@ class ChineseDefaults(Language.Defaults):
use_jieba = True
tokenizer_exceptions = BASE_EXCEPTIONS
stop_words = STOP_WORDS
writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
class Chinese(Language):
lang = "zh"

1
spacy/language.py
View File

@ -94,6 +94,7 @@ class BaseDefaults(object):
morph_rules = {}
lex_attr_getters = LEX_ATTRS
syntax_iterators = {}
writing_system = {"direction": "ltr", "has_case": True, "has_letters": True}
class Language(object):

26
spacy/lexeme.pyx
View File

@ -161,17 +161,17 @@ cdef class Lexeme:
Lexeme.c_from_bytes(self.c, lex_data)
self.orth = self.c.orth
property has_vector:
@property
def has_vector(self):
"""RETURNS (bool): Whether a word vector is associated with the object.
"""
def __get__(self):
return self.vocab.has_vector(self.c.orth)
return self.vocab.has_vector(self.c.orth)
property vector_norm:
@property
def vector_norm(self):
"""RETURNS (float): The L2 norm of the vector representation."""
def __get__(self):
vector = self.vector
return numpy.sqrt((vector**2).sum())
vector = self.vector
return numpy.sqrt((vector**2).sum())
property vector:
"""A real-valued meaning representation.
@ -209,17 +209,17 @@ cdef class Lexeme:
def __set__(self, float sentiment):
self.c.sentiment = sentiment
property orth_:
@property
def orth_(self):
"""RETURNS (unicode): The original verbatim text of the lexeme
(identical to `Lexeme.text`). Exists mostly for consistency with
the other attributes."""
def __get__(self):
return self.vocab.strings[self.c.orth]
return self.vocab.strings[self.c.orth]
property text:
@property
def text(self):
"""RETURNS (unicode): The original verbatim text of the lexeme."""
def __get__(self):
return self.orth_
return self.orth_
property lower:
"""RETURNS (unicode): Lowercase form of the lexeme."""

8
spacy/syntax/arc_eager.pyx
View File

@ -369,9 +369,9 @@ cdef class ArcEager(TransitionSystem):
actions[LEFT].setdefault('dep', 0)
return actions
property action_types:
def __get__(self):
return (SHIFT, REDUCE, LEFT, RIGHT, BREAK)
@property
def action_types(self):
return (SHIFT, REDUCE, LEFT, RIGHT, BREAK)
def get_cost(self, StateClass state, GoldParse gold, action):
cdef Transition t = self.lookup_transition(action)
@ -384,7 +384,7 @@ cdef class ArcEager(TransitionSystem):
cdef Transition t = self.lookup_transition(action)
t.do(state.c, t.label)
return state
def is_gold_parse(self, StateClass state, GoldParse gold):
predicted = set()
truth = set()

6
spacy/syntax/ner.pyx
View File

@ -80,9 +80,9 @@ cdef class BiluoPushDown(TransitionSystem):
actions[action][label] += 1
return actions
property action_types:
def __get__(self):
return (BEGIN, IN, LAST, UNIT, OUT)
@property
def action_types(self):
return (BEGIN, IN, LAST, UNIT, OUT)
def move_name(self, int move, attr_t label):
if move == OUT:

68
spacy/tests/test_displacy.py Normal file
View File

@ -0,0 +1,68 @@
# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy import displacy
from spacy.tokens import Span
from .util import get_doc
def test_displacy_parse_ents(en_vocab):
"""Test that named entities on a Doc are converted into displaCy's format."""
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
ents = displacy.parse_ents(doc)
assert isinstance(ents, dict)
assert ents["text"] == "But Google is starting from behind "
assert ents["ents"] == [{"start": 4, "end": 10, "label": "ORG"}]
def test_displacy_parse_deps(en_vocab):
"""Test that deps and tags on a Doc are converted into displaCy's format."""
words = ["This", "is", "a", "sentence"]
heads = [1, 0, 1, -2]
pos = ["DET", "VERB", "DET", "NOUN"]
tags = ["DT", "VBZ", "DT", "NN"]
deps = ["nsubj", "ROOT", "det", "attr"]
doc = get_doc(en_vocab, words=words, heads=heads, pos=pos, tags=tags, deps=deps)
deps = displacy.parse_deps(doc)
assert isinstance(deps, dict)
assert deps["words"] == [
{"text": "This", "tag": "DET"},
{"text": "is", "tag": "VERB"},
{"text": "a", "tag": "DET"},
{"text": "sentence", "tag": "NOUN"},
]
assert deps["arcs"] == [
{"start": 0, "end": 1, "label": "nsubj", "dir": "left"},
{"start": 2, "end": 3, "label": "det", "dir": "left"},
{"start": 1, "end": 3, "label": "attr", "dir": "right"},
]
def test_displacy_spans(en_vocab):
"""Test that displaCy can render Spans."""
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
html = displacy.render(doc[1:4], style="ent")
assert html.startswith("<div")
def test_displacy_render_wrapper(en_vocab):
"""Test that displaCy accepts custom rendering wrapper."""
def wrapper(html):
return "TEST" + html + "TEST"
displacy.set_render_wrapper(wrapper)
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
html = displacy.render(doc, style="ent")
assert html.startswith("TEST<div")
assert html.endswith("/div>TEST")
def test_displacy_raises_for_wrong_type(en_vocab):
with pytest.raises(ValueError):
displacy.render("hello world")

64
spacy/tests/test_misc.py
View File

@ -4,13 +4,9 @@ from __future__ import unicode_literals
import pytest
from pathlib import Path
from spacy import util
from spacy import displacy
from spacy import prefer_gpu, require_gpu
from spacy.tokens import Span
from spacy._ml import PrecomputableAffine
from .util import get_doc
@pytest.mark.parametrize("text", ["hello/world", "hello world"])
def test_util_ensure_path_succeeds(text):
@ -31,66 +27,6 @@ def test_util_get_package_path(package):
assert isinstance(path, Path)
def test_displacy_parse_ents(en_vocab):
"""Test that named entities on a Doc are converted into displaCy's format."""
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
ents = displacy.parse_ents(doc)
assert isinstance(ents, dict)
assert ents["text"] == "But Google is starting from behind "
assert ents["ents"] == [{"start": 4, "end": 10, "label": "ORG"}]
def test_displacy_parse_deps(en_vocab):
"""Test that deps and tags on a Doc are converted into displaCy's format."""
words = ["This", "is", "a", "sentence"]
heads = [1, 0, 1, -2]
pos = ["DET", "VERB", "DET", "NOUN"]
tags = ["DT", "VBZ", "DT", "NN"]
deps = ["nsubj", "ROOT", "det", "attr"]
doc = get_doc(en_vocab, words=words, heads=heads, pos=pos, tags=tags, deps=deps)
deps = displacy.parse_deps(doc)
assert isinstance(deps, dict)
assert deps["words"] == [
{"text": "This", "tag": "DET"},
{"text": "is", "tag": "VERB"},
{"text": "a", "tag": "DET"},
{"text": "sentence", "tag": "NOUN"},
]
assert deps["arcs"] == [
{"start": 0, "end": 1, "label": "nsubj", "dir": "left"},
{"start": 2, "end": 3, "label": "det", "dir": "left"},
{"start": 1, "end": 3, "label": "attr", "dir": "right"},
]
def test_displacy_spans(en_vocab):
"""Test that displaCy can render Spans."""
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
html = displacy.render(doc[1:4], style="ent")
assert html.startswith("<div")
def test_displacy_render_wrapper(en_vocab):
"""Test that displaCy accepts custom rendering wrapper."""
def wrapper(html):
return "TEST" + html + "TEST"
displacy.set_render_wrapper(wrapper)
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])]
html = displacy.render(doc, style="ent")
assert html.startswith("TEST<div")
assert html.endswith("/div>TEST")
def test_displacy_raises_for_wrong_type(en_vocab):
with pytest.raises(ValueError):
displacy.render("hello world")
def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
model = PrecomputableAffine(nO=nO, nI=nI, nF=nF, nP=nP)
assert model.W.shape == (nF, nO, nP, nI)

5
spacy/tests/vocab_vectors/test_vocab_api.py
View File

@ -45,3 +45,8 @@ def test_vocab_api_contains(en_vocab, text):
_ = en_vocab[text] # noqa: F841
assert text in en_vocab
assert "LKsdjvlsakdvlaksdvlkasjdvljasdlkfvm" not in en_vocab
def test_vocab_writing_system(en_vocab):
assert en_vocab.writing_system["direction"] == "ltr"
assert en_vocab.writing_system["has_case"] is True

90
spacy/tokens/doc.pyx
View File

@ -384,7 +384,8 @@ cdef class Doc:
xp = get_array_module(vector)
return xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm)
property has_vector:
@property
def has_vector(self):
"""A boolean value indicating whether a word vector is associated with
the object.
@ -392,15 +393,14 @@ cdef class Doc:
DOCS: https://spacy.io/api/doc#has_vector
"""
def __get__(self):
if "has_vector" in self.user_hooks:
return self.user_hooks["has_vector"](self)
elif self.vocab.vectors.data.size:
return True
elif self.tensor.size:
return True
else:
return False
if "has_vector" in self.user_hooks:
return self.user_hooks["has_vector"](self)
elif self.vocab.vectors.data.size:
return True
elif self.tensor.size:
return True
else:
return False
property vector:
"""A real-valued meaning representation. Defaults to an average of the
@ -453,22 +453,22 @@ cdef class Doc:
def __set__(self, value):
self._vector_norm = value
property text:
@property
def text(self):
"""A unicode representation of the document text.
RETURNS (unicode): The original verbatim text of the document.
"""
def __get__(self):
return "".join(t.text_with_ws for t in self)
return "".join(t.text_with_ws for t in self)
property text_with_ws:
@property
def text_with_ws(self):
"""An alias of `Doc.text`, provided for duck-type compatibility with
`Span` and `Token`.
RETURNS (unicode): The original verbatim text of the document.
"""
def __get__(self):
return self.text
return self.text
property ents:
"""The named entities in the document. Returns a tuple of named entity
@ -545,7 +545,8 @@ cdef class Doc:
# Set start as B
self.c[start].ent_iob = 3
property noun_chunks:
@property
def noun_chunks(self):
"""Iterate over the base noun phrases in the document. Yields base
noun-phrase #[code Span] objects, if the document has been
syntactically parsed. A base noun phrase, or "NP chunk", is a noun
@ -557,22 +558,22 @@ cdef class Doc:
DOCS: https://spacy.io/api/doc#noun_chunks
"""
def __get__(self):
if not self.is_parsed:
raise ValueError(Errors.E029)
# Accumulate the result before beginning to iterate over it. This
# prevents the tokenisation from being changed out from under us
# during the iteration. The tricky thing here is that Span accepts
# its tokenisation changing, so it's okay once we have the Span
# objects. See Issue #375.
spans = []
if self.noun_chunks_iterator is not None:
for start, end, label in self.noun_chunks_iterator(self):
spans.append(Span(self, start, end, label=label))
for span in spans:
yield span
if not self.is_parsed:
raise ValueError(Errors.E029)
# Accumulate the result before beginning to iterate over it. This
# prevents the tokenisation from being changed out from under us
# during the iteration. The tricky thing here is that Span accepts
# its tokenisation changing, so it's okay once we have the Span
# objects. See Issue #375.
spans = []
if self.noun_chunks_iterator is not None:
for start, end, label in self.noun_chunks_iterator(self):
spans.append(Span(self, start, end, label=label))
for span in spans:
yield span
property sents:
@property
def sents(self):
"""Iterate over the sentences in the document. Yields sentence `Span`
objects. Sentence spans have no label. To improve accuracy on informal
texts, spaCy calculates sentence boundaries from the syntactic
@ -583,19 +584,18 @@ cdef class Doc:
DOCS: https://spacy.io/api/doc#sents
"""
def __get__(self):
if not self.is_sentenced:
raise ValueError(Errors.E030)
if "sents" in self.user_hooks:
yield from self.user_hooks["sents"](self)
else:
start = 0
for i in range(1, self.length):
if self.c[i].sent_start == 1:
yield Span(self, start, i)
start = i
if start != self.length:
yield Span(self, start, self.length)
if not self.is_sentenced:
raise ValueError(Errors.E030)
if "sents" in self.user_hooks:
yield from self.user_hooks["sents"](self)
else:
start = 0
for i in range(1, self.length):
if self.c[i].sent_start == 1:
yield Span(self, start, i)
start = i
if start != self.length:
yield Span(self, start, self.length)
@property
def lang(self):

352
spacy/tokens/span.pyx
View File

@ -322,46 +322,47 @@ cdef class Span:
self.start = start
self.end = end + 1
property vocab:
@property
def vocab(self):
"""RETURNS (Vocab): The Span's Doc's vocab."""
def __get__(self):
return self.doc.vocab
return self.doc.vocab
property sent:
@property
def sent(self):
"""RETURNS (Span): The sentence span that the span is a part of."""
def __get__(self):
if "sent" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["sent"](self)
# This should raise if not parsed / no custom sentence boundaries
self.doc.sents
# If doc is parsed we can use the deps to find the sentence
# otherwise we use the `sent_start` token attribute
cdef int n = 0
cdef int i
if self.doc.is_parsed:
root = &self.doc.c[self.start]
while root.head != 0:
root += root.head
n += 1
if n >= self.doc.length:
raise RuntimeError(Errors.E038)
return self.doc[root.l_edge:root.r_edge + 1]
elif self.doc.is_sentenced:
# Find start of the sentence
start = self.start
while self.doc.c[start].sent_start != 1 and start > 0:
start += -1
# Find end of the sentence
end = self.end
n = 0
while end < self.doc.length and self.doc.c[end].sent_start != 1:
end += 1
n += 1
if n >= self.doc.length:
break
return self.doc[start:end]
if "sent" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["sent"](self)
# This should raise if not parsed / no custom sentence boundaries
self.doc.sents
# If doc is parsed we can use the deps to find the sentence
# otherwise we use the `sent_start` token attribute
cdef int n = 0
cdef int i
if self.doc.is_parsed:
root = &self.doc.c[self.start]
while root.head != 0:
root += root.head
n += 1
if n >= self.doc.length:
raise RuntimeError(Errors.E038)
return self.doc[root.l_edge:root.r_edge + 1]
elif self.doc.is_sentenced:
# Find start of the sentence
start = self.start
while self.doc.c[start].sent_start != 1 and start > 0:
start += -1
# Find end of the sentence
end = self.end
n = 0
while end < self.doc.length and self.doc.c[end].sent_start != 1:
end += 1
n += 1
if n >= self.doc.length:
break
return self.doc[start:end]
property ents:
@property
def ents(self):
"""The named entities in the span. Returns a tuple of named entity
`Span` objects, if the entity recognizer has been applied.
@ -369,14 +370,14 @@ cdef class Span:
DOCS: https://spacy.io/api/span#ents
"""
def __get__(self):
ents = []
for ent in self.doc.ents:
if ent.start >= self.start and ent.end <= self.end:
ents.append(ent)
return ents
ents = []
for ent in self.doc.ents:
if ent.start >= self.start and ent.end <= self.end:
ents.append(ent)
return ents
property has_vector:
@property
def has_vector(self):
"""A boolean value indicating whether a word vector is associated with
the object.
@ -384,17 +385,17 @@ cdef class Span:
DOCS: https://spacy.io/api/span#has_vector
"""
def __get__(self):
if "has_vector" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["has_vector"](self)
elif self.vocab.vectors.data.size > 0:
return any(token.has_vector for token in self)
elif self.doc.tensor.size > 0:
return True
else:
return False
if "has_vector" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["has_vector"](self)
elif self.vocab.vectors.data.size > 0:
return any(token.has_vector for token in self)
elif self.doc.tensor.size > 0:
return True
else:
return False
property vector:
@property
def vector(self):
"""A real-valued meaning representation. Defaults to an average of the
token vectors.
@ -403,61 +404,61 @@ cdef class Span:
DOCS: https://spacy.io/api/span#vector
"""
def __get__(self):
if "vector" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["vector"](self)
if self._vector is None:
self._vector = sum(t.vector for t in self) / len(self)
return self._vector
if "vector" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["vector"](self)
if self._vector is None:
self._vector = sum(t.vector for t in self) / len(self)
return self._vector
property vector_norm:
@property
def vector_norm(self):
"""The L2 norm of the span's vector representation.
RETURNS (float): The L2 norm of the vector representation.
DOCS: https://spacy.io/api/span#vector_norm
"""
def __get__(self):
if "vector_norm" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["vector"](self)
cdef float value
cdef double norm = 0
if self._vector_norm is None:
norm = 0
for value in self.vector:
norm += value * value
self._vector_norm = sqrt(norm) if norm != 0 else 0
return self._vector_norm
if "vector_norm" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["vector"](self)
cdef float value
cdef double norm = 0
if self._vector_norm is None:
norm = 0
for value in self.vector:
norm += value * value
self._vector_norm = sqrt(norm) if norm != 0 else 0
return self._vector_norm
property sentiment:
@property
def sentiment(self):
"""RETURNS (float): A scalar value indicating the positivity or
negativity of the span.
"""
def __get__(self):
if "sentiment" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["sentiment"](self)
else:
return sum([token.sentiment for token in self]) / len(self)
if "sentiment" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["sentiment"](self)
else:
return sum([token.sentiment for token in self]) / len(self)
property text:
@property
def text(self):
"""RETURNS (unicode): The original verbatim text of the span."""
def __get__(self):
text = self.text_with_ws
if self[-1].whitespace_:
text = text[:-1]
return text
text = self.text_with_ws
if self[-1].whitespace_:
text = text[:-1]
return text
property text_with_ws:
@property
def text_with_ws(self):
"""The text content of the span with a trailing whitespace character if
the last token has one.
RETURNS (unicode): The text content of the span (with trailing
whitespace).
"""
def __get__(self):
return "".join([t.text_with_ws for t in self])
return "".join([t.text_with_ws for t in self])
property noun_chunks:
@property
def noun_chunks(self):
"""Yields base noun-phrase `Span` objects, if the document has been
syntactically parsed. A base noun phrase, or "NP chunk", is a noun
phrase that does not permit other NPs to be nested within it – so no
@ -468,23 +469,23 @@ cdef class Span:
DOCS: https://spacy.io/api/span#noun_chunks
"""
def __get__(self):
if not self.doc.is_parsed:
raise ValueError(Errors.E029)
# Accumulate the result before beginning to iterate over it. This
# prevents the tokenisation from being changed out from under us
# during the iteration. The tricky thing here is that Span accepts
# its tokenisation changing, so it's okay once we have the Span
# objects. See Issue #375
spans = []
cdef attr_t label
if self.doc.noun_chunks_iterator is not None:
for start, end, label in self.doc.noun_chunks_iterator(self):
spans.append(Span(self.doc, start, end, label=label))
for span in spans:
yield span
if not self.doc.is_parsed:
raise ValueError(Errors.E029)
# Accumulate the result before beginning to iterate over it. This
# prevents the tokenisation from being changed out from under us
# during the iteration. The tricky thing here is that Span accepts
# its tokenisation changing, so it's okay once we have the Span
# objects. See Issue #375
spans = []
cdef attr_t label
if self.doc.noun_chunks_iterator is not None:
for start, end, label in self.doc.noun_chunks_iterator(self):
spans.append(Span(self.doc, start, end, label=label))
for span in spans:
yield span
property root:
@property
def root(self):
"""The token with the shortest path to the root of the
sentence (or the root itself). If multiple tokens are equally
high in the tree, the first token is taken.
@ -493,41 +494,41 @@ cdef class Span:
DOCS: https://spacy.io/api/span#root
"""
def __get__(self):
self._recalculate_indices()
if "root" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["root"](self)
# This should probably be called 'head', and the other one called
# 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/
cdef int i
# First, we scan through the Span, and check whether there's a word
# with head==0, i.e. a sentence root. If so, we can return it. The
# longer the span, the more likely it contains a sentence root, and
# in this case we return in linear time.
for i in range(self.start, self.end):
if self.doc.c[i].head == 0:
return self.doc[i]
# If we don't have a sentence root, we do something that's not so
# algorithmically clever, but I think should be quite fast,
# especially for short spans.
# For each word, we count the path length, and arg min this measure.
# We could use better tree logic to save steps here...But I
# think this should be okay.
cdef int current_best = self.doc.length
cdef int root = -1
for i in range(self.start, self.end):
if self.start <= (i+self.doc.c[i].head) < self.end:
continue
words_to_root = _count_words_to_root(&self.doc.c[i], self.doc.length)
if words_to_root < current_best:
current_best = words_to_root
root = i
if root == -1:
return self.doc[self.start]
else:
return self.doc[root]
self._recalculate_indices()
if "root" in self.doc.user_span_hooks:
return self.doc.user_span_hooks["root"](self)
# This should probably be called 'head', and the other one called
# 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/
cdef int i
# First, we scan through the Span, and check whether there's a word
# with head==0, i.e. a sentence root. If so, we can return it. The
# longer the span, the more likely it contains a sentence root, and
# in this case we return in linear time.
for i in range(self.start, self.end):
if self.doc.c[i].head == 0:
return self.doc[i]
# If we don't have a sentence root, we do something that's not so
# algorithmically clever, but I think should be quite fast,
# especially for short spans.
# For each word, we count the path length, and arg min this measure.
# We could use better tree logic to save steps here...But I
# think this should be okay.
cdef int current_best = self.doc.length
cdef int root = -1
for i in range(self.start, self.end):
if self.start <= (i+self.doc.c[i].head) < self.end:
continue
words_to_root = _count_words_to_root(&self.doc.c[i], self.doc.length)
if words_to_root < current_best:
current_best = words_to_root
root = i
if root == -1:
return self.doc[self.start]
else:
return self.doc[root]
property lefts:
@property
def lefts(self):
"""Tokens that are to the left of the span, whose head is within the
`Span`.
@ -535,13 +536,13 @@ cdef class Span:
DOCS: https://spacy.io/api/span#lefts
"""
def __get__(self):
for token in reversed(self): # Reverse, so we get tokens in order
for left in token.lefts:
if left.i < self.start:
yield left
for token in reversed(self): # Reverse, so we get tokens in order
for left in token.lefts:
if left.i < self.start:
yield left
property rights:
@property
def rights(self):
"""Tokens that are to the right of the Span, whose head is within the
`Span`.
@ -549,13 +550,13 @@ cdef class Span:
DOCS: https://spacy.io/api/span#rights
"""
def __get__(self):
for token in self:
for right in token.rights:
if right.i >= self.end:
yield right
for token in self:
for right in token.rights:
if right.i >= self.end:
yield right
property n_lefts:
@property
def n_lefts(self):
"""The number of tokens that are to the left of the span, whose
heads are within the span.
@ -564,10 +565,10 @@ cdef class Span:
DOCS: https://spacy.io/api/span#n_lefts
"""
def __get__(self):
return len(list(self.lefts))
return len(list(self.lefts))
property n_rights:
@property
def n_rights(self):
"""The number of tokens that are to the right of the span, whose
heads are within the span.
@ -576,22 +577,21 @@ cdef class Span:
DOCS: https://spacy.io/api/span#n_rights
"""
def __get__(self):
return len(list(self.rights))
return len(list(self.rights))
property subtree:
@property
def subtree(self):
"""Tokens within the span and tokens which descend from them.
YIELDS (Token): A token within the span, or a descendant from it.
DOCS: https://spacy.io/api/span#subtree
"""
def __get__(self):
for word in self.lefts:
yield from word.subtree
yield from self
for word in self.rights:
yield from word.subtree
for word in self.lefts:
yield from word.subtree
yield from self
for word in self.rights:
yield from word.subtree
property ent_id:
"""RETURNS (uint64): The entity ID."""
@ -609,33 +609,33 @@ cdef class Span:
def __set__(self, hash_t key):
raise NotImplementedError(TempErrors.T007.format(attr="ent_id_"))
property orth_:
@property
def orth_(self):
"""Verbatim text content (identical to `Span.text`). Exists mostly for
consistency with other attributes.
RETURNS (unicode): The span's text."""
def __get__(self):
return self.text
return self.text
property lemma_:
@property
def lemma_(self):
"""RETURNS (unicode): The span's lemma."""
def __get__(self):
return " ".join([t.lemma_ for t in self]).strip()
return " ".join([t.lemma_ for t in self]).strip()
property upper_:
@property
def upper_(self):
"""Deprecated. Use `Span.text.upper()` instead."""
def __get__(self):
return "".join([t.text_with_ws.upper() for t in self]).strip()
return "".join([t.text_with_ws.upper() for t in self]).strip()
property lower_:
@property
def lower_(self):
"""Deprecated. Use `Span.text.lower()` instead."""
def __get__(self):
return "".join([t.text_with_ws.lower() for t in self]).strip()
return "".join([t.text_with_ws.lower() for t in self]).strip()
property string:
@property
def string(self):
"""Deprecated: Use `Span.text_with_ws` instead."""
def __get__(self):
return "".join([t.text_with_ws for t in self])
return "".join([t.text_with_ws for t in self])
property label_:
"""RETURNS (unicode): The span's label."""

487
spacy/tokens/token.pyx
View File

@ -218,111 +218,111 @@ cdef class Token:
xp = get_array_module(vector)
return (xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm))
property lex_id:
@property
def lex_id(self):
"""RETURNS (int): Sequential ID of the token's lexical type."""
def __get__(self):
return self.c.lex.id
return self.c.lex.id
property rank:
@property
def rank(self):
"""RETURNS (int): Sequential ID of the token's lexical type, used to
index into tables, e.g. for word vectors."""
def __get__(self):
return self.c.lex.id
return self.c.lex.id
property string:
@property
def string(self):
"""Deprecated: Use Token.text_with_ws instead."""
def __get__(self):
return self.text_with_ws
return self.text_with_ws
property text:
@property
def text(self):
"""RETURNS (unicode): The original verbatim text of the token."""
def __get__(self):
return self.orth_
return self.orth_
property text_with_ws:
@property
def text_with_ws(self):
"""RETURNS (unicode): The text content of the span (with trailing
whitespace).
"""
def __get__(self):
cdef unicode orth = self.vocab.strings[self.c.lex.orth]
if self.c.spacy:
return orth + " "
else:
return orth
cdef unicode orth = self.vocab.strings[self.c.lex.orth]
if self.c.spacy:
return orth + " "
else:
return orth
property prob:
@property
def prob(self):
"""RETURNS (float): Smoothed log probability estimate of token type."""
def __get__(self):
return self.c.lex.prob
return self.c.lex.prob
property sentiment:
@property
def sentiment(self):
"""RETURNS (float): A scalar value indicating the positivity or
negativity of the token."""
def __get__(self):
if "sentiment" in self.doc.user_token_hooks:
return self.doc.user_token_hooks["sentiment"](self)
return self.c.lex.sentiment
if "sentiment" in self.doc.user_token_hooks:
return self.doc.user_token_hooks["sentiment"](self)
return self.c.lex.sentiment
property lang:
@property
def lang(self):
"""RETURNS (uint64): ID of the language of the parent document's
vocabulary.
"""
def __get__(self):
return self.c.lex.lang
return self.c.lex.lang
property idx:
@property
def idx(self):
"""RETURNS (int): The character offset of the token within the parent
document.
"""
def __get__(self):
return self.c.idx
return self.c.idx
property cluster:
@property
def cluster(self):
"""RETURNS (int): Brown cluster ID."""
def __get__(self):
return self.c.lex.cluster
return self.c.lex.cluster
property orth:
@property
def orth(self):
"""RETURNS (uint64): ID of the verbatim text content."""
def __get__(self):
return self.c.lex.orth
return self.c.lex.orth
property lower:
@property
def lower(self):
"""RETURNS (uint64): ID of the lowercase token text."""
def __get__(self):
return self.c.lex.lower
return self.c.lex.lower
property norm:
@property
def norm(self):
"""RETURNS (uint64): ID of the token's norm, i.e. a normalised form of
the token text. Usually set in the language's tokenizer exceptions
or norm exceptions.
"""
def __get__(self):
if self.c.norm == 0:
return self.c.lex.norm
else:
return self.c.norm
if self.c.norm == 0:
return self.c.lex.norm
else:
return self.c.norm
property shape:
@property
def shape(self):
"""RETURNS (uint64): ID of the token's shape, a transform of the
tokens's string, to show orthographic features (e.g. "Xxxx", "dd").
"""
def __get__(self):
return self.c.lex.shape
return self.c.lex.shape
property prefix:
@property
def prefix(self):
"""RETURNS (uint64): ID of a length-N substring from the start of the
token. Defaults to `N=1`.
"""
def __get__(self):
return self.c.lex.prefix
return self.c.lex.prefix
property suffix:
@property
def suffix(self):
"""RETURNS (uint64): ID of a length-N substring from the end of the
token. Defaults to `N=3`.
"""
def __get__(self):
return self.c.lex.suffix
return self.c.lex.suffix
property lemma:
"""RETURNS (uint64): ID of the base form of the word, with no
@ -362,7 +362,8 @@ cdef class Token:
def __set__(self, attr_t label):
self.c.dep = label
property has_vector:
@property
def has_vector(self):
"""A boolean value indicating whether a word vector is associated with
the object.
@ -370,14 +371,14 @@ cdef class Token:
DOCS: https://spacy.io/api/token#has_vector
"""
def __get__(self):
if 'has_vector' in self.doc.user_token_hooks:
return self.doc.user_token_hooks["has_vector"](self)
if self.vocab.vectors.size == 0 and self.doc.tensor.size != 0:
return True
return self.vocab.has_vector(self.c.lex.orth)
if "has_vector" in self.doc.user_token_hooks:
return self.doc.user_token_hooks["has_vector"](self)
if self.vocab.vectors.size == 0 and self.doc.tensor.size != 0:
return True
return self.vocab.has_vector(self.c.lex.orth)
property vector:
@property
def vector(self):
"""A real-valued meaning representation.
RETURNS (numpy.ndarray[ndim=1, dtype='float32']): A 1D numpy array
@ -385,28 +386,28 @@ cdef class Token:
DOCS: https://spacy.io/api/token#vector
"""
def __get__(self):
if 'vector' in self.doc.user_token_hooks:
return self.doc.user_token_hooks["vector"](self)
if self.vocab.vectors.size == 0 and self.doc.tensor.size != 0:
return self.doc.tensor[self.i]
else:
return self.vocab.get_vector(self.c.lex.orth)
if "vector" in self.doc.user_token_hooks:
return self.doc.user_token_hooks["vector"](self)
if self.vocab.vectors.size == 0 and self.doc.tensor.size != 0:
return self.doc.tensor[self.i]
else:
return self.vocab.get_vector(self.c.lex.orth)
property vector_norm:
@property
def vector_norm(self):
"""The L2 norm of the token's vector representation.
RETURNS (float): The L2 norm of the vector representation.
DOCS: https://spacy.io/api/token#vector_norm
"""
def __get__(self):
if 'vector_norm' in self.doc.user_token_hooks:
return self.doc.user_token_hooks["vector_norm"](self)
vector = self.vector
return numpy.sqrt((vector ** 2).sum())
if "vector_norm" in self.doc.user_token_hooks:
return self.doc.user_token_hooks["vector_norm"](self)
vector = self.vector
return numpy.sqrt((vector ** 2).sum())
property n_lefts:
@property
def n_lefts(self):
"""The number of leftward immediate children of the word, in the
syntactic dependency parse.
@ -415,10 +416,10 @@ cdef class Token:
DOCS: https://spacy.io/api/token#n_lefts
"""
def __get__(self):
return self.c.l_kids
return self.c.l_kids
property n_rights:
@property
def n_rights(self):
"""The number of rightward immediate children of the word, in the
syntactic dependency parse.
@ -427,15 +428,14 @@ cdef class Token:
DOCS: https://spacy.io/api/token#n_rights
"""
def __get__(self):
return self.c.r_kids
return self.c.r_kids
property sent:
@property
def sent(self):
"""RETURNS (Span): The sentence span that the token is a part of."""
def __get__(self):
if 'sent' in self.doc.user_token_hooks:
return self.doc.user_token_hooks["sent"](self)
return self.doc[self.i : self.i+1].sent
if 'sent' in self.doc.user_token_hooks:
return self.doc.user_token_hooks["sent"](self)
return self.doc[self.i : self.i+1].sent
property sent_start:
def __get__(self):
@ -479,7 +479,8 @@ cdef class Token:
else:
raise ValueError(Errors.E044.format(value=value))
property lefts:
@property
def lefts(self):
"""The leftward immediate children of the word, in the syntactic
dependency parse.
@ -487,19 +488,19 @@ cdef class Token:
DOCS: https://spacy.io/api/token#lefts
"""
def __get__(self):
cdef int nr_iter = 0
cdef const TokenC* ptr = self.c - (self.i - self.c.l_edge)
while ptr < self.c:
if ptr + ptr.head == self.c:
yield self.doc[ptr - (self.c - self.i)]
ptr += 1
nr_iter += 1
# This is ugly, but it's a way to guard out infinite loops
if nr_iter >= 10000000:
raise RuntimeError(Errors.E045.format(attr="token.lefts"))
cdef int nr_iter = 0
cdef const TokenC* ptr = self.c - (self.i - self.c.l_edge)
while ptr < self.c:
if ptr + ptr.head == self.c:
yield self.doc[ptr - (self.c - self.i)]
ptr += 1
nr_iter += 1
# This is ugly, but it's a way to guard out infinite loops
if nr_iter >= 10000000:
raise RuntimeError(Errors.E045.format(attr="token.lefts"))
property rights:
@property
def rights(self):
"""The rightward immediate children of the word, in the syntactic
dependency parse.
@ -507,33 +508,33 @@ cdef class Token:
DOCS: https://spacy.io/api/token#rights
"""
def __get__(self):
cdef const TokenC* ptr = self.c + (self.c.r_edge - self.i)
tokens = []
cdef int nr_iter = 0
while ptr > self.c:
if ptr + ptr.head == self.c:
tokens.append(self.doc[ptr - (self.c - self.i)])
ptr -= 1
nr_iter += 1
if nr_iter >= 10000000:
raise RuntimeError(Errors.E045.format(attr="token.rights"))
tokens.reverse()
for t in tokens:
yield t
cdef const TokenC* ptr = self.c + (self.c.r_edge - self.i)
tokens = []
cdef int nr_iter = 0
while ptr > self.c:
if ptr + ptr.head == self.c:
tokens.append(self.doc[ptr - (self.c - self.i)])
ptr -= 1
nr_iter += 1
if nr_iter >= 10000000:
raise RuntimeError(Errors.E045.format(attr="token.rights"))
tokens.reverse()
for t in tokens:
yield t
property children:
@property
def children(self):
"""A sequence of the token's immediate syntactic children.
YIELDS (Token): A child token such that `child.head==self`.
DOCS: https://spacy.io/api/token#children
"""
def __get__(self):
yield from self.lefts
yield from self.rights
yield from self.lefts
yield from self.rights
property subtree:
@property
def subtree(self):
"""A sequence containing the token and all the token's syntactic
descendants.
@ -542,30 +543,30 @@ cdef class Token:
DOCS: https://spacy.io/api/token#subtree
"""
def __get__(self):
for word in self.lefts:
yield from word.subtree
yield self
for word in self.rights:
yield from word.subtree
for word in self.lefts:
yield from word.subtree
yield self
for word in self.rights:
yield from word.subtree
property left_edge:
@property
def left_edge(self):
"""The leftmost token of this token's syntactic descendents.
RETURNS (Token): The first token such that `self.is_ancestor(token)`.
"""
def __get__(self):
return self.doc[self.c.l_edge]
return self.doc[self.c.l_edge]
property right_edge:
@property
def right_edge(self):
"""The rightmost token of this token's syntactic descendents.
RETURNS (Token): The last token such that `self.is_ancestor(token)`.
"""
def __get__(self):
return self.doc[self.c.r_edge]
return self.doc[self.c.r_edge]
property ancestors:
@property
def ancestors(self):
"""A sequence of this token's syntactic ancestors.
YIELDS (Token): A sequence of ancestor tokens such that
@ -573,15 +574,14 @@ cdef class Token:
DOCS: https://spacy.io/api/token#ancestors
"""
def __get__(self):
cdef const TokenC* head_ptr = self.c
# Guard against infinite loop, no token can have
# more ancestors than tokens in the tree.
cdef int i = 0
while head_ptr.head != 0 and i < self.doc.length:
head_ptr += head_ptr.head
yield self.doc[head_ptr - (self.c - self.i)]
i += 1
cdef const TokenC* head_ptr = self.c
# Guard against infinite loop, no token can have
# more ancestors than tokens in the tree.
cdef int i = 0
while head_ptr.head != 0 and i < self.doc.length:
head_ptr += head_ptr.head
yield self.doc[head_ptr - (self.c - self.i)]
i += 1
def is_ancestor(self, descendant):
"""Check whether this token is a parent, grandparent, etc. of another
@ -685,23 +685,23 @@ cdef class Token:
# Set new head
self.c.head = rel_newhead_i
property conjuncts:
@property
def conjuncts(self):
"""A sequence of coordinated tokens, including the token itself.
YIELDS (Token): A coordinated token.
DOCS: https://spacy.io/api/token#conjuncts
"""
def __get__(self):
cdef Token word
if "conjuncts" in self.doc.user_token_hooks:
yield from self.doc.user_token_hooks["conjuncts"](self)
else:
if self.dep != conj:
for word in self.rights:
if word.dep == conj:
yield word
yield from word.conjuncts
cdef Token word
if "conjuncts" in self.doc.user_token_hooks:
yield from self.doc.user_token_hooks["conjuncts"](self)
else:
if self.dep != conj:
for word in self.rights:
if word.dep == conj:
yield word
yield from word.conjuncts
property ent_type:
"""RETURNS (uint64): Named entity type."""
@ -711,15 +711,6 @@ cdef class Token:
def __set__(self, ent_type):
self.c.ent_type = ent_type
property ent_iob:
"""IOB code of named entity tag. `1="I", 2="O", 3="B"`. 0 means no tag
is assigned.
RETURNS (uint64): IOB code of named entity tag.
"""
def __get__(self):
return self.c.ent_iob
property ent_type_:
"""RETURNS (unicode): Named entity type."""
def __get__(self):
@ -728,16 +719,25 @@ cdef class Token:
def __set__(self, ent_type):
self.c.ent_type = self.vocab.strings.add(ent_type)
property ent_iob_:
@property
def ent_iob(self):
"""IOB code of named entity tag. `1="I", 2="O", 3="B"`. 0 means no tag
is assigned.
RETURNS (uint64): IOB code of named entity tag.
"""
return self.c.ent_iob
@property
def ent_iob_(self):
"""IOB code of named entity tag. "B" means the token begins an entity,
"I" means it is inside an entity, "O" means it is outside an entity,
and "" means no entity tag is set.
RETURNS (unicode): IOB code of named entity tag.
"""
def __get__(self):
iob_strings = ("", "I", "O", "B")
return iob_strings[self.c.ent_iob]
iob_strings = ("", "I", "O", "B")
return iob_strings[self.c.ent_iob]
property ent_id:
"""RETURNS (uint64): ID of the entity the token is an instance of,
@ -759,26 +759,25 @@ cdef class Token:
def __set__(self, name):
self.c.ent_id = self.vocab.strings.add(name)
property whitespace_:
"""RETURNS (unicode): The trailing whitespace character, if present.
"""
def __get__(self):
return " " if self.c.spacy else ""
@property
def whitespace_(self):
"""RETURNS (unicode): The trailing whitespace character, if present."""
return " " if self.c.spacy else ""
property orth_:
@property
def orth_(self):
"""RETURNS (unicode): Verbatim text content (identical to
`Token.text`). Exists mostly for consistency with the other
attributes.
"""
def __get__(self):
return self.vocab.strings[self.c.lex.orth]
return self.vocab.strings[self.c.lex.orth]
property lower_:
@property
def lower_(self):
"""RETURNS (unicode): The lowercase token text. Equivalent to
`Token.text.lower()`.
"""
def __get__(self):
return self.vocab.strings[self.c.lex.lower]
return self.vocab.strings[self.c.lex.lower]
property norm_:
"""RETURNS (unicode): The token's norm, i.e. a normalised form of the
@ -791,33 +790,33 @@ cdef class Token:
def __set__(self, unicode norm_):
self.c.norm = self.vocab.strings.add(norm_)
property shape_:
@property
def shape_(self):
"""RETURNS (unicode): Transform of the tokens's string, to show
orthographic features. For example, "Xxxx" or "dd".
"""
def __get__(self):
return self.vocab.strings[self.c.lex.shape]
return self.vocab.strings[self.c.lex.shape]
property prefix_:
@property
def prefix_(self):
"""RETURNS (unicode): A length-N substring from the start of the token.
Defaults to `N=1`.
"""
def __get__(self):
return self.vocab.strings[self.c.lex.prefix]
return self.vocab.strings[self.c.lex.prefix]
property suffix_:
@property
def suffix_(self):
"""RETURNS (unicode): A length-N substring from the end of the token.
Defaults to `N=3`.
"""
def __get__(self):
return self.vocab.strings[self.c.lex.suffix]
return self.vocab.strings[self.c.lex.suffix]
property lang_:
@property
def lang_(self):
"""RETURNS (unicode): Language of the parent document's vocabulary,
e.g. 'en'.
"""
def __get__(self):
return self.vocab.strings[self.c.lex.lang]
return self.vocab.strings[self.c.lex.lang]
property lemma_:
"""RETURNS (unicode): The token lemma, i.e. the base form of the word,
@ -856,110 +855,110 @@ cdef class Token:
def __set__(self, unicode label):
self.c.dep = self.vocab.strings.add(label)
property is_oov:
@property
def is_oov(self):
"""RETURNS (bool): Whether the token is out-of-vocabulary."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_OOV)
return Lexeme.c_check_flag(self.c.lex, IS_OOV)
property is_stop:
@property
def is_stop(self):
"""RETURNS (bool): Whether the token is a stop word, i.e. part of a
"stop list" defined by the language data.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_STOP)
return Lexeme.c_check_flag(self.c.lex, IS_STOP)
property is_alpha:
@property
def is_alpha(self):
"""RETURNS (bool): Whether the token consists of alpha characters.
Equivalent to `token.text.isalpha()`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_ALPHA)
return Lexeme.c_check_flag(self.c.lex, IS_ALPHA)
property is_ascii:
@property
def is_ascii(self):
"""RETURNS (bool): Whether the token consists of ASCII characters.
Equivalent to `[any(ord(c) >= 128 for c in token.text)]`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_ASCII)
return Lexeme.c_check_flag(self.c.lex, IS_ASCII)
property is_digit:
@property
def is_digit(self):
"""RETURNS (bool): Whether the token consists of digits. Equivalent to
`token.text.isdigit()`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_DIGIT)
return Lexeme.c_check_flag(self.c.lex, IS_DIGIT)
property is_lower:
@property
def is_lower(self):
"""RETURNS (bool): Whether the token is in lowercase. Equivalent to
`token.text.islower()`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_LOWER)
return Lexeme.c_check_flag(self.c.lex, IS_LOWER)
property is_upper:
@property
def is_upper(self):
"""RETURNS (bool): Whether the token is in uppercase. Equivalent to
`token.text.isupper()`
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_UPPER)
return Lexeme.c_check_flag(self.c.lex, IS_UPPER)
property is_title:
@property
def is_title(self):
"""RETURNS (bool): Whether the token is in titlecase. Equivalent to
`token.text.istitle()`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_TITLE)
return Lexeme.c_check_flag(self.c.lex, IS_TITLE)
property is_punct:
@property
def is_punct(self):
"""RETURNS (bool): Whether the token is punctuation."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_PUNCT)
return Lexeme.c_check_flag(self.c.lex, IS_PUNCT)
property is_space:
@property
def is_space(self):
"""RETURNS (bool): Whether the token consists of whitespace characters.
Equivalent to `token.text.isspace()`.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_SPACE)
return Lexeme.c_check_flag(self.c.lex, IS_SPACE)
property is_bracket:
@property
def is_bracket(self):
"""RETURNS (bool): Whether the token is a bracket."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_BRACKET)
return Lexeme.c_check_flag(self.c.lex, IS_BRACKET)
property is_quote:
@property
def is_quote(self):
"""RETURNS (bool): Whether the token is a quotation mark."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_QUOTE)
return Lexeme.c_check_flag(self.c.lex, IS_QUOTE)
property is_left_punct:
@property
def is_left_punct(self):
"""RETURNS (bool): Whether the token is a left punctuation mark."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_LEFT_PUNCT)
return Lexeme.c_check_flag(self.c.lex, IS_LEFT_PUNCT)
property is_right_punct:
@property
def is_right_punct(self):
"""RETURNS (bool): Whether the token is a right punctuation mark."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_RIGHT_PUNCT)
return Lexeme.c_check_flag(self.c.lex, IS_RIGHT_PUNCT)
property is_currency:
@property
def is_currency(self):
"""RETURNS (bool): Whether the token is a currency symbol."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, IS_CURRENCY)
return Lexeme.c_check_flag(self.c.lex, IS_CURRENCY)
property like_url:
@property
def like_url(self):
"""RETURNS (bool): Whether the token resembles a URL."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, LIKE_URL)
return Lexeme.c_check_flag(self.c.lex, LIKE_URL)
property like_num:
@property
def like_num(self):
"""RETURNS (bool): Whether the token resembles a number, e.g. "10.9",
"10", "ten", etc.
"""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, LIKE_NUM)
return Lexeme.c_check_flag(self.c.lex, LIKE_NUM)
property like_email:
@property
def like_email(self):
"""RETURNS (bool): Whether the token resembles an email address."""
def __get__(self):
return Lexeme.c_check_flag(self.c.lex, LIKE_EMAIL)
return Lexeme.c_check_flag(self.c.lex, LIKE_EMAIL)

12
spacy/util.py
View File

@ -38,6 +38,18 @@ def set_env_log(value):
_PRINT_ENV = value
def lang_class_is_loaded(lang):
"""Check whether a Language class is already loaded. Language classes are
loaded lazily, to avoid expensive setup code associated with the language
data.
lang (unicode): Two-letter language code, e.g. 'en'.
RETURNS (bool): Whether a Language class has been loaded.
"""
global LANGUAGES
return lang in LANGUAGES
def get_lang_class(lang):
"""Import and load a Language class.

21
spacy/vocab.pyx
View File

@ -60,12 +60,23 @@ cdef class Vocab:
self.morphology = Morphology(self.strings, tag_map, lemmatizer)
self.vectors = Vectors()
property lang:
@property
def lang(self):
langfunc = None
if self.lex_attr_getters:
langfunc = self.lex_attr_getters.get(LANG, None)
return langfunc("_") if langfunc else ""
property writing_system:
"""A dict with information about the language's writing system. To get
the data, we use the vocab.lang property to fetch the Language class.
If the Language class is not loaded, an empty dict is returned.
"""
def __get__(self):
langfunc = None
if self.lex_attr_getters:
langfunc = self.lex_attr_getters.get(LANG, None)
return langfunc("_") if langfunc else ""
if not util.lang_class_is_loaded(self.lang):
return {}
lang_class = util.get_lang_class(self.lang)
return dict(lang_class.Defaults.writing_system)
def __len__(self):
"""The current number of lexemes stored.

18
website/docs/api/top-level.md
View File

@ -351,6 +351,24 @@ the two-letter language code.
| `name` | unicode | Two-letter language code, e.g. `'en'`. |
| `cls` | `Language` | The language class, e.g. `English`. |
### util.lang_class_is_loaded (#util.lang_class_is_loaded tag="function" new="2.1")
Check whether a `Language` class is already loaded. `Language` classes are
loaded lazily, to avoid expensive setup code associated with the language data.
> #### Example
>
> ```python
> lang_cls = util.get_lang_class("en")
> assert util.lang_class_is_loaded("en") is True
> assert util.lang_class_is_loaded("de") is False
> ```
| Name | Type | Description |
| ----------- | ------- | -------------------------------------- |
| `name` | unicode | Two-letter language code, e.g. `'en'`. |
| **RETURNS** | bool | Whether the class has been loaded. |
### util.load_model {#util.load_model tag="function" new="2"}
Load a model from a shortcut link, package or data path. If called with a

11
website/docs/api/vocab.md
View File

@ -288,11 +288,12 @@ Load state from a binary string.
> assert type(PERSON) == int
> ```
| Name | Type | Description |
| ------------------------------------ | ------------- | --------------------------------------------- |
| `strings` | `StringStore` | A table managing the string-to-int mapping. |
| `vectors` <Tag variant="new">2</Tag> | `Vectors` | A table associating word IDs to word vectors. |
| `vectors_length` | int | Number of dimensions for each word vector. |
| Name | Type | Description |
| --------------------------------------------- | ------------- | ------------------------------------------------------------ |
| `strings` | `StringStore` | A table managing the string-to-int mapping. |
| `vectors` <Tag variant="new">2</Tag> | `Vectors` | A table associating word IDs to word vectors. |
| `vectors_length` | int | Number of dimensions for each word vector. |
| `writing_system` <Tag variant="new">2.1</Tag> | dict | A dict with information about the language's writing system. |
## Serialization fields {#serialization-fields}