explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream_master' into sync_develop

Browse Source
This commit is contained in:
svlandeg 2023-07-19 12:08:52 +02:00
commit 79ec68f01b
71 changed files with 879 additions and 609 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/tests.yml vendored
View File

@ -45,6 +45,12 @@ jobs:
run: |
python -m pip install flake8==5.0.4
python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
- name: cython-lint
run: |
python -m pip install cython-lint -c requirements.txt
# E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
cython-lint spacy --ignore E501,W291,E266
tests:
name: Test
needs: Validate

4
Makefile
View File

@ -1,11 +1,11 @@
SHELL := /bin/bash
ifndef SPACY_EXTRAS
override SPACY_EXTRAS = spacy-lookups-data==1.0.2 jieba spacy-pkuseg==0.0.28 sudachipy sudachidict_core pymorphy2
override SPACY_EXTRAS = spacy-lookups-data==1.0.3
endif
ifndef PYVER
override PYVER = 3.6
override PYVER = 3.8
endif
VENV := ./env$(PYVER)

1
requirements.txt
View File

@ -39,4 +39,5 @@ types-setuptools>=57.0.0
types-requests
types-setuptools>=57.0.0
black==22.3.0
cython-lint>=0.15.0; python_version >= "3.7"
isort>=5.0,<6.0

2
spacy/attrs.pxd
View File

@ -96,4 +96,4 @@ cdef enum attr_id_t:
ENT_ID = symbols.ENT_ID
IDX
SENT_END
SENT_END

2
spacy/attrs.pyx
View File

@ -117,7 +117,7 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
if "pos" in stringy_attrs:
stringy_attrs["TAG"] = stringy_attrs.pop("pos")
if "morph" in stringy_attrs:
morphs = stringy_attrs.pop("morph")
morphs = stringy_attrs.pop("morph") # no-cython-lint
if "number" in stringy_attrs:
stringy_attrs.pop("number")
if "tenspect" in stringy_attrs:

3
spacy/displacy/render.py
View File

@ -1,4 +1,3 @@
import itertools
import uuid
from typing import Any, Dict, List, Optional, Tuple, Union
@ -218,7 +217,7 @@ class SpanRenderer:
+ (self.offset_step * (len(entities) - 1))
)
markup += self.span_template.format(
text=token["text"],
text=escape_html(token["text"]),
span_slices=slices,
span_starts=starts,
total_height=total_height,

3
spacy/kb/candidate.pxd
View File

@ -4,7 +4,8 @@ from ..typedefs cimport hash_t
from .kb cimport KnowledgeBase
# Object used by the Entity Linker that summarizes one entity-alias candidate combination.
# Object used by the Entity Linker that summarizes one entity-alias candidate
# combination.
cdef class Candidate:
cdef readonly KnowledgeBase kb
cdef hash_t entity_hash

27
spacy/kb/candidate.pyx
View File

@ -8,15 +8,24 @@ from ..tokens import Span
cdef class Candidate:
"""A `Candidate` object refers to a textual mention (`alias`) that may or may not be resolved
to a specific `entity` from a Knowledge Base. This will be used as input for the entity linking
algorithm which will disambiguate the various candidates to the correct one.
"""A `Candidate` object refers to a textual mention (`alias`) that may or
may not be resolved to a specific `entity` from a Knowledge Base. This
will be used as input for the entity linking algorithm which will
disambiguate the various candidates to the correct one.
Each candidate (alias, entity) pair is assigned a certain prior probability.
DOCS: https://spacy.io/api/kb/#candidate-init
"""
def __init__(self, KnowledgeBase kb, entity_hash, entity_freq, entity_vector, alias_hash, prior_prob):
def __init__(
self,
KnowledgeBase kb,
entity_hash,
entity_freq,
entity_vector,
alias_hash,
prior_prob
):
self.kb = kb
self.entity_hash = entity_hash
self.entity_freq = entity_freq
@ -59,7 +68,8 @@ cdef class Candidate:
def get_candidates(kb: KnowledgeBase, mention: Span) -> Iterable[Candidate]:
"""
Return candidate entities for a given mention and fetching appropriate entries from the index.
Return candidate entities for a given mention and fetching appropriate
entries from the index.
kb (KnowledgeBase): Knowledge base to query.
mention (Span): Entity mention for which to identify candidates.
RETURNS (Iterable[Candidate]): Identified candidates.
@ -67,9 +77,12 @@ def get_candidates(kb: KnowledgeBase, mention: Span) -> Iterable[Candidate]:
return kb.get_candidates(mention)
def get_candidates_batch(kb: KnowledgeBase, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]:
def get_candidates_batch(
kb: KnowledgeBase, mentions: Iterable[Span]
) -> Iterable[Iterable[Candidate]]:
"""
Return candidate entities for the given mentions and fetching appropriate entries from the index.
Return candidate entities for the given mentions and fetching appropriate entries
from the index.
kb (KnowledgeBase): Knowledge base to query.
mention (Iterable[Span]): Entity mentions for which to identify candidates.
RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.

49
spacy/kb/kb.pyx
View File

@ -12,8 +12,9 @@ from .candidate import Candidate
cdef class KnowledgeBase:
"""A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases,
to support entity linking of named entities to real-world concepts.
"""A `KnowledgeBase` instance stores unique identifiers for entities and
their textual aliases, to support entity linking of named entities to
real-world concepts.
This is an abstract class and requires its operations to be implemented.
DOCS: https://spacy.io/api/kb
@ -31,10 +32,13 @@ cdef class KnowledgeBase:
self.entity_vector_length = entity_vector_length
self.mem = Pool()
def get_candidates_batch(self, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]:
def get_candidates_batch(
self, mentions: Iterable[Span]
) -> Iterable[Iterable[Candidate]]:
"""
Return candidate entities for specified texts. Each candidate defines the entity, the original alias,
and the prior probability of that alias resolving to that entity.
Return candidate entities for specified texts. Each candidate defines
the entity, the original alias, and the prior probability of that
alias resolving to that entity.
If no candidate is found for a given text, an empty list is returned.
mentions (Iterable[Span]): Mentions for which to get candidates.
RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.
@ -43,14 +47,17 @@ cdef class KnowledgeBase:
def get_candidates(self, mention: Span) -> Iterable[Candidate]:
"""
Return candidate entities for specified text. Each candidate defines the entity, the original alias,
Return candidate entities for specified text. Each candidate defines
the entity, the original alias,
and the prior probability of that alias resolving to that entity.
If the no candidate is found for a given text, an empty list is returned.
mention (Span): Mention for which to get candidates.
RETURNS (Iterable[Candidate]): Identified candidates.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_candidates", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="get_candidates", name=self.__name__
)
)
def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]:
@ -68,7 +75,9 @@ cdef class KnowledgeBase:
RETURNS (Iterable[float]): Vector for specified entity.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_vector", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="get_vector", name=self.__name__
)
)
def to_bytes(self, **kwargs) -> bytes:
@ -76,7 +85,9 @@ cdef class KnowledgeBase:
RETURNS (bytes): Current state as binary string.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_bytes", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="to_bytes", name=self.__name__
)
)
def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()):
@ -85,25 +96,35 @@ cdef class KnowledgeBase:
exclude (Tuple[str]): Properties to exclude when restoring KB.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_bytes", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="from_bytes", name=self.__name__
)
)
def to_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None:
def to_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
"""
Write KnowledgeBase content to disk.
path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_disk", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="to_disk", name=self.__name__
)
)
def from_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None:
def from_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
"""
Load KnowledgeBase content from disk.
path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_disk", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="from_disk", name=self.__name__
)
)

62
spacy/kb/kb_in_memory.pxd
View File

@ -55,23 +55,28 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# optional data, we can let users configure a DB as the backend for this.
cdef object _features_table
cdef inline int64_t c_add_vector(self, vector[float] entity_vector) nogil:
"""Add an entity vector to the vectors table."""
cdef int64_t new_index = self._vectors_table.size()
self._vectors_table.push_back(entity_vector)
return new_index
cdef inline int64_t c_add_entity(self, hash_t entity_hash, float freq,
int32_t vector_index, int feats_row) nogil:
cdef inline int64_t c_add_entity(
self,
hash_t entity_hash,
float freq,
int32_t vector_index,
int feats_row
) nogil:
"""Add an entry to the vector of entries.
After calling this method, make sure to update also the _entry_index using the return value"""
After calling this method, make sure to update also the _entry_index
using the return value"""
# This is what we'll map the entity hash key to. It's where the entry will sit
# in the vector of entries, so we can get it later.
cdef int64_t new_index = self._entries.size()
# Avoid struct initializer to enable nogil, cf https://github.com/cython/cython/issues/1642
# Avoid struct initializer to enable nogil, cf.
# https://github.com/cython/cython/issues/1642
cdef KBEntryC entry
entry.entity_hash = entity_hash
entry.vector_index = vector_index
@ -81,11 +86,17 @@ cdef class InMemoryLookupKB(KnowledgeBase):
self._entries.push_back(entry)
return new_index
cdef inline int64_t c_add_aliases(self, hash_t alias_hash, vector[int64_t] entry_indices, vector[float] probs) nogil:
"""Connect a mention to a list of potential entities with their prior probabilities .
After calling this method, make sure to update also the _alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be defined
# in the vector of aliases.
cdef inline int64_t c_add_aliases(
self,
hash_t alias_hash,
vector[int64_t] entry_indices,
vector[float] probs
) nogil:
"""Connect a mention to a list of potential entities with their prior
probabilities. After calling this method, make sure to update also the
_alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be
# defined in the vector of aliases.
cdef int64_t new_index = self._aliases_table.size()
# Avoid struct initializer to enable nogil
@ -98,8 +109,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef inline void _create_empty_vectors(self, hash_t dummy_hash) nogil:
"""
Initializing the vectors and making sure the first element of each vector is a dummy,
because the PreshMap maps pointing to indices in these vectors can not contain 0 as value
Initializing the vectors and making sure the first element of each vector is a
dummy, because the PreshMap maps pointing to indices in these vectors can not
contain 0 as value.
cf. https://github.com/explosion/preshed/issues/17
"""
cdef int32_t dummy_value = 0
@ -130,12 +142,18 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef class Writer:
cdef FILE* _fp
cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1
cdef int write_header(
self, int64_t nr_entries, int64_t entity_vector_length
) except -1
cdef int write_vector_element(self, float element) except -1
cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1
cdef int write_entry(
self, hash_t entry_hash, float entry_freq, int32_t vector_index
) except -1
cdef int write_alias_length(self, int64_t alias_length) except -1
cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1
cdef int write_alias_header(
self, hash_t alias_hash, int64_t candidate_length
) except -1
cdef int write_alias(self, int64_t entry_index, float prob) except -1
cdef int _write(self, void* value, size_t size) except -1
@ -143,12 +161,18 @@ cdef class Writer:
cdef class Reader:
cdef FILE* _fp
cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1
cdef int read_header(
self, int64_t* nr_entries, int64_t* entity_vector_length
) except -1
cdef int read_vector_element(self, float* element) except -1
cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1
cdef int read_entry(
self, hash_t* entity_hash, float* freq, int32_t* vector_index
) except -1
cdef int read_alias_length(self, int64_t* alias_length) except -1
cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1
cdef int read_alias_header(
self, hash_t* alias_hash, int64_t* candidate_length
) except -1
cdef int read_alias(self, int64_t* entry_index, float* prob) except -1
cdef int _read(self, void* value, size_t size) except -1

154
spacy/kb/kb_in_memory.pyx
View File

@ -1,5 +1,5 @@
# cython: infer_types=True, profile=True
from typing import Any, Callable, Dict, Iterable, Union
from typing import Any, Callable, Dict, Iterable
import srsly
@ -27,8 +27,9 @@ from .candidate import Candidate as Candidate
cdef class InMemoryLookupKB(KnowledgeBase):
"""An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
to support entity linking of named entities to real-world concepts.
"""An `InMemoryLookupKB` instance stores unique identifiers for entities
and their textual aliases, to support entity linking of named entities to
real-world concepts.
DOCS: https://spacy.io/api/inmemorylookupkb
"""
@ -71,7 +72,8 @@ cdef class InMemoryLookupKB(KnowledgeBase):
def add_entity(self, str entity, float freq, vector[float] entity_vector):
"""
Add an entity to the KB, optionally specifying its log probability based on corpus frequency
Add an entity to the KB, optionally specifying its log probability
based on corpus frequency.
Return the hash of the entity ID/name at the end.
"""
cdef hash_t entity_hash = self.vocab.strings.add(entity)
@ -83,14 +85,20 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# Raise an error if the provided entity vector is not of the correct length
if len(entity_vector) != self.entity_vector_length:
raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
raise ValueError(
Errors.E141.format(
found=len(entity_vector), required=self.entity_vector_length
)
)
vector_index = self.c_add_vector(entity_vector=entity_vector)
new_index = self.c_add_entity(entity_hash=entity_hash,
freq=freq,
vector_index=vector_index,
feats_row=-1) # Features table currently not implemented
new_index = self.c_add_entity(
entity_hash=entity_hash,
freq=freq,
vector_index=vector_index,
feats_row=-1
) # Features table currently not implemented
self._entry_index[entity_hash] = new_index
return entity_hash
@ -115,7 +123,12 @@ cdef class InMemoryLookupKB(KnowledgeBase):
else:
entity_vector = vector_list[i]
if len(entity_vector) != self.entity_vector_length:
raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
raise ValueError(
Errors.E141.format(
found=len(entity_vector),
required=self.entity_vector_length
)
)
entry.entity_hash = entity_hash
entry.freq = freq_list[i]
@ -149,11 +162,15 @@ cdef class InMemoryLookupKB(KnowledgeBase):
previous_alias_nr = self.get_size_aliases()
# Throw an error if the length of entities and probabilities are not the same
if not len(entities) == len(probabilities):
raise ValueError(Errors.E132.format(alias=alias,
entities_length=len(entities),
probabilities_length=len(probabilities)))
raise ValueError(
Errors.E132.format(
alias=alias,
entities_length=len(entities),
probabilities_length=len(probabilities))
)
# Throw an error if the probabilities sum up to more than 1 (allow for some rounding errors)
# Throw an error if the probabilities sum up to more than 1 (allow for
# some rounding errors)
prob_sum = sum(probabilities)
if prob_sum > 1.00001:
raise ValueError(Errors.E133.format(alias=alias, sum=prob_sum))
@ -170,40 +187,47 @@ cdef class InMemoryLookupKB(KnowledgeBase):
for entity, prob in zip(entities, probabilities):
entity_hash = self.vocab.strings[entity]
if not entity_hash in self._entry_index:
if entity_hash not in self._entry_index:
raise ValueError(Errors.E134.format(entity=entity))
entry_index = <int64_t>self._entry_index.get(entity_hash)
entry_indices.push_back(int(entry_index))
probs.push_back(float(prob))
new_index = self.c_add_aliases(alias_hash=alias_hash, entry_indices=entry_indices, probs=probs)
new_index = self.c_add_aliases(
alias_hash=alias_hash, entry_indices=entry_indices, probs=probs
)
self._alias_index[alias_hash] = new_index
if previous_alias_nr + 1 != self.get_size_aliases():
raise RuntimeError(Errors.E891.format(alias=alias))
return alias_hash
def append_alias(self, str alias, str entity, float prior_prob, ignore_warnings=False):
def append_alias(
self, str alias, str entity, float prior_prob, ignore_warnings=False
):
"""
For an alias already existing in the KB, extend its potential entities with one more.
For an alias already existing in the KB, extend its potential entities
with one more.
Throw a warning if either the alias or the entity is unknown,
or when the combination is already previously recorded.
Throw an error if this entity+prior prob would exceed the sum of 1.
For efficiency, it's best to use the method `add_alias` as much as possible instead of this one.
For efficiency, it's best to use the method `add_alias` as much as
possible instead of this one.
"""
# Check if the alias exists in the KB
cdef hash_t alias_hash = self.vocab.strings[alias]
if not alias_hash in self._alias_index:
if alias_hash not in self._alias_index:
raise ValueError(Errors.E176.format(alias=alias))
# Check if the entity exists in the KB
cdef hash_t entity_hash = self.vocab.strings[entity]
if not entity_hash in self._entry_index:
if entity_hash not in self._entry_index:
raise ValueError(Errors.E134.format(entity=entity))
entry_index = <int64_t>self._entry_index.get(entity_hash)
# Throw an error if the prior probabilities (including the new one) sum up to more than 1
# Throw an error if the prior probabilities (including the new one)
# sum up to more than 1
alias_index = <int64_t>self._alias_index.get(alias_hash)
alias_entry = self._aliases_table[alias_index]
current_sum = sum([p for p in alias_entry.probs])
@ -236,12 +260,13 @@ cdef class InMemoryLookupKB(KnowledgeBase):
def get_alias_candidates(self, str alias) -> Iterable[Candidate]:
"""
Return candidate entities for an alias. Each candidate defines the entity, the original alias,
and the prior probability of that alias resolving to that entity.
Return candidate entities for an alias. Each candidate defines the
entity, the original alias, and the prior probability of that alias
resolving to that entity.
If the alias is not known in the KB, and empty list is returned.
"""
cdef hash_t alias_hash = self.vocab.strings[alias]
if not alias_hash in self._alias_index:
if alias_hash not in self._alias_index:
return []
alias_index = <int64_t>self._alias_index.get(alias_hash)
alias_entry = self._aliases_table[alias_index]
@ -249,10 +274,14 @@ cdef class InMemoryLookupKB(KnowledgeBase):
return [Candidate(kb=self,
entity_hash=self._entries[entry_index].entity_hash,
entity_freq=self._entries[entry_index].freq,
entity_vector=self._vectors_table[self._entries[entry_index].vector_index],
entity_vector=self._vectors_table[
self._entries[entry_index].vector_index
],
alias_hash=alias_hash,
prior_prob=prior_prob)
for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs)
for (entry_index, prior_prob) in zip(
alias_entry.entry_indices, alias_entry.probs
)
if entry_index != 0]
def get_vector(self, str entity):
@ -266,8 +295,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
return self._vectors_table[self._entries[entry_index].vector_index]
def get_prior_prob(self, str entity, str alias):
""" Return the prior probability of a given alias being linked to a given entity,
or return 0.0 when this combination is not known in the knowledge base"""
""" Return the prior probability of a given alias being linked to a
given entity, or return 0.0 when this combination is not known in the
knowledge base."""
cdef hash_t alias_hash = self.vocab.strings[alias]
cdef hash_t entity_hash = self.vocab.strings[entity]
@ -278,7 +308,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
entry_index = self._entry_index[entity_hash]
alias_entry = self._aliases_table[alias_index]
for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs):
for (entry_index, prior_prob) in zip(
alias_entry.entry_indices, alias_entry.probs
):
if self._entries[entry_index].entity_hash == entity_hash:
return prior_prob
@ -288,13 +320,19 @@ cdef class InMemoryLookupKB(KnowledgeBase):
"""Serialize the current state to a binary string.
"""
def serialize_header():
header = (self.get_size_entities(), self.get_size_aliases(), self.entity_vector_length)
header = (
self.get_size_entities(),
self.get_size_aliases(),
self.entity_vector_length
)
return srsly.json_dumps(header)
def serialize_entries():
i = 1
tuples = []
for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
for entry_hash, entry_index in sorted(
self._entry_index.items(), key=lambda x: x[1]
):
entry = self._entries[entry_index]
assert entry.entity_hash == entry_hash
assert entry_index == i
@ -307,7 +345,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
headers = []
indices_lists = []
probs_lists = []
for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
for alias_hash, alias_index in sorted(
self._alias_index.items(), key=lambda x: x[1]
):
alias = self._aliases_table[alias_index]
assert alias_index == i
candidate_length = len(alias.entry_indices)
@ -365,7 +405,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
indices = srsly.json_loads(all_data[1])
probs = srsly.json_loads(all_data[2])
for header, indices, probs in zip(headers, indices, probs):
alias_hash, candidate_length = header
alias_hash, _candidate_length = header
alias.entry_indices = indices
alias.probs = probs
self._aliases_table[i] = alias
@ -414,10 +454,14 @@ cdef class InMemoryLookupKB(KnowledgeBase):
writer.write_vector_element(element)
i = i+1
# dumping the entry records in the order in which they are in the _entries vector.
# index 0 is a dummy object not stored in the _entry_index and can be ignored.
# dumping the entry records in the order in which they are in the
# _entries vector.
# index 0 is a dummy object not stored in the _entry_index and can
# be ignored.
i = 1
for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
for entry_hash, entry_index in sorted(
self._entry_index.items(), key=lambda x: x[1]
):
entry = self._entries[entry_index]
assert entry.entity_hash == entry_hash
assert entry_index == i
@ -429,7 +473,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# dumping the aliases in the order in which they are in the _alias_index vector.
# index 0 is a dummy object not stored in the _aliases_table and can be ignored.
i = 1
for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
for alias_hash, alias_index in sorted(
self._alias_index.items(), key=lambda x: x[1]
):
alias = self._aliases_table[alias_index]
assert alias_index == i
@ -535,7 +581,8 @@ cdef class Writer:
def __init__(self, path):
assert isinstance(path, Path)
content = bytes(path)
cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
cdef bytes bytes_loc = content.encode('utf8') \
if type(content) == str else content
self._fp = fopen(<char*>bytes_loc, 'wb')
if not self._fp:
raise IOError(Errors.E146.format(path=path))
@ -545,14 +592,18 @@ cdef class Writer:
cdef size_t status = fclose(self._fp)
assert status == 0
cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1:
cdef int write_header(
self, int64_t nr_entries, int64_t entity_vector_length
) except -1:
self._write(&nr_entries, sizeof(nr_entries))
self._write(&entity_vector_length, sizeof(entity_vector_length))
cdef int write_vector_element(self, float element) except -1:
self._write(&element, sizeof(element))
cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1:
cdef int write_entry(
self, hash_t entry_hash, float entry_freq, int32_t vector_index
) except -1:
self._write(&entry_hash, sizeof(entry_hash))
self._write(&entry_freq, sizeof(entry_freq))
self._write(&vector_index, sizeof(vector_index))
@ -561,7 +612,9 @@ cdef class Writer:
cdef int write_alias_length(self, int64_t alias_length) except -1:
self._write(&alias_length, sizeof(alias_length))
cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1:
cdef int write_alias_header(
self, hash_t alias_hash, int64_t candidate_length
) except -1:
self._write(&alias_hash, sizeof(alias_hash))
self._write(&candidate_length, sizeof(candidate_length))
@ -577,16 +630,19 @@ cdef class Writer:
cdef class Reader:
def __init__(self, path):
content = bytes(path)
cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
cdef bytes bytes_loc = content.encode('utf8') \
if type(content) == str else content
self._fp = fopen(<char*>bytes_loc, 'rb')
if not self._fp:
PyErr_SetFromErrno(IOError)
status = fseek(self._fp, 0, 0) # this can be 0 if there is no header
fseek(self._fp, 0, 0) # this can be 0 if there is no header
def __dealloc__(self):
fclose(self._fp)
cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1:
cdef int read_header(
self, int64_t* nr_entries, int64_t* entity_vector_length
) except -1:
status = self._read(nr_entries, sizeof(int64_t))
if status < 1:
if feof(self._fp):
@ -606,7 +662,9 @@ cdef class Reader:
return 0 # end of file
raise IOError(Errors.E145.format(param="vector element"))
cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1:
cdef int read_entry(
self, hash_t* entity_hash, float* freq, int32_t* vector_index
) except -1:
status = self._read(entity_hash, sizeof(hash_t))
if status < 1:
if feof(self._fp):
@ -637,7 +695,9 @@ cdef class Reader:
return 0 # end of file
raise IOError(Errors.E145.format(param="alias length"))
cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1:
cdef int read_alias_header(
self, hash_t* alias_hash, int64_t* candidate_length
) except -1:
status = self._read(alias_hash, sizeof(hash_t))
if status < 1:
if feof(self._fp):

3
spacy/language.py
View File

@ -1826,7 +1826,6 @@ class Language:
# Later we replace the component config with the raw config again.
interpolated = filled.interpolate() if not filled.is_interpolated else filled
pipeline = interpolated.get("components", {})
sourced = util.get_sourced_components(interpolated)
# If components are loaded from a source (existing models), we cache
# them here so they're only loaded once
source_nlps = {}
@ -1959,7 +1958,7 @@ class Language:
useful when training a pipeline with components sourced from an existing
pipeline: if multiple components (e.g. tagger, parser, NER) listen to
the same tok2vec component, but some of them are frozen and not updated,
their performance may degrade significally as the tok2vec component is
their performance may degrade significantly as the tok2vec component is
updated with new data. To prevent this, listeners can be replaced with
a standalone tok2vec layer that is owned by the component and doesn't
change if the component isn't updated.

17
spacy/lexeme.pyx
View File

@ -1,7 +1,6 @@
# cython: embedsignature=True
# Compiler crashes on memory view coercion without this. Should report bug.
cimport numpy as np
from cython.view cimport array as cvarray
from libc.string cimport memset
np.import_array()
@ -35,7 +34,7 @@ from .typedefs cimport attr_t, flags_t
from .attrs import intify_attrs
from .errors import Errors, Warnings
OOV_RANK = 0xffffffffffffffff # UINT64_MAX
OOV_RANK = 0xffffffffffffffff # UINT64_MAX
memset(&EMPTY_LEXEME, 0, sizeof(LexemeC))
EMPTY_LEXEME.id = OOV_RANK
@ -105,7 +104,7 @@ cdef class Lexeme:
if isinstance(value, float):
continue
elif isinstance(value, (int, long)):
Lexeme.set_struct_attr(self.c, attr, value)
Lexeme.set_struct_attr(self.c, attr, value)
else:
Lexeme.set_struct_attr(self.c, attr, self.vocab.strings.add(value))
@ -137,10 +136,12 @@ cdef class Lexeme:
if hasattr(other, "orth"):
if self.c.orth == other.orth:
return 1.0
elif hasattr(other, "__len__") and len(other) == 1 \
and hasattr(other[0], "orth"):
if self.c.orth == other[0].orth:
return 1.0
elif (
hasattr(other, "__len__") and len(other) == 1
and hasattr(other[0], "orth")
and self.c.orth == other[0].orth
):
return 1.0
if self.vector_norm == 0 or other.vector_norm == 0:
warnings.warn(Warnings.W008.format(obj="Lexeme"))
return 0.0
@ -149,7 +150,7 @@ cdef class Lexeme:
result = xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm)
# ensure we get a scalar back (numpy does this automatically but cupy doesn't)
return result.item()
@property
def has_vector(self):
"""RETURNS (bool): Whether a word vector is associated with the object.

10
spacy/matcher/dependencymatcher.pyx
View File

@ -108,7 +108,7 @@ cdef class DependencyMatcher:
key (str): The match ID.
RETURNS (bool): Whether the matcher contains rules for this match ID.
"""
return self.has_key(key)
return self.has_key(key) # no-cython-lint: W601
def _validate_input(self, pattern, key):
idx = 0
@ -264,7 +264,7 @@ cdef class DependencyMatcher:
def remove(self, key):
key = self._normalize_key(key)
if not key in self._patterns:
if key not in self._patterns:
raise ValueError(Errors.E175.format(key=key))
self._patterns.pop(key)
self._raw_patterns.pop(key)
@ -382,7 +382,7 @@ cdef class DependencyMatcher:
return []
return [doc[node].head]
def _gov(self,doc,node):
def _gov(self, doc, node):
return list(doc[node].children)
def _dep_chain(self, doc, node):
@ -443,7 +443,7 @@ cdef class DependencyMatcher:
def _right_child(self, doc, node):
return [child for child in doc[node].rights]
def _left_child(self, doc, node):
return [child for child in doc[node].lefts]
@ -461,7 +461,7 @@ cdef class DependencyMatcher:
if doc[node].head.i > node:
return [doc[node].head]
return []
def _left_parent(self, doc, node):
if doc[node].head.i < node:
return [doc[node].head]

246
spacy/matcher/matcher.pyx
View File

@ -12,31 +12,18 @@ import warnings
import srsly
from ..attrs cimport (
DEP,
ENT_IOB,
ID,
LEMMA,
MORPH,
NULL_ATTR,
ORTH,
POS,
TAG,
attr_id_t,
)
from ..attrs cimport DEP, ENT_IOB, ID, LEMMA, MORPH, NULL_ATTR, POS, TAG
from ..structs cimport TokenC
from ..tokens.doc cimport Doc, get_token_attr_for_matcher
from ..tokens.morphanalysis cimport MorphAnalysis
from ..tokens.span cimport Span
from ..tokens.token cimport Token
from ..typedefs cimport attr_t
from ..vocab cimport Vocab
from ..attrs import IDS
from ..errors import Errors, MatchPatternError, Warnings
from ..schemas import validate_token_pattern
from ..strings import get_string_id
from ..util import registry
from .levenshtein import levenshtein_compare
DEF PADDING = 5
@ -87,9 +74,9 @@ cdef class Matcher:
key (str): The match ID.
RETURNS (bool): Whether the matcher contains rules for this match ID.
"""
return self.has_key(key)
return self.has_key(key) # no-cython-lint: W601
def add(self, key, patterns, *, on_match=None, greedy: str=None):
def add(self, key, patterns, *, on_match=None, greedy: str = None):
"""Add a match-rule to the matcher. A match-rule consists of: an ID
key, an on_match callback, and one or more patterns.
@ -143,8 +130,13 @@ cdef class Matcher:
key = self._normalize_key(key)
for pattern in patterns:
try:
specs = _preprocess_pattern(pattern, self.vocab,
self._extensions, self._extra_predicates, self._fuzzy_compare)
specs = _preprocess_pattern(
pattern,
self.vocab,
self._extensions,
self._extra_predicates,
self._fuzzy_compare
)
self.patterns.push_back(init_pattern(self.mem, key, specs))
for spec in specs:
for attr, _ in spec[1]:
@ -168,7 +160,7 @@ cdef class Matcher:
key (str): The ID of the match rule.
"""
norm_key = self._normalize_key(key)
if not norm_key in self._patterns:
if norm_key not in self._patterns:
raise ValueError(Errors.E175.format(key=key))
self._patterns.pop(norm_key)
self._callbacks.pop(norm_key)
@ -268,8 +260,15 @@ cdef class Matcher:
if self.patterns.empty():
matches = []
else:
matches = find_matches(&self.patterns[0], self.patterns.size(), doclike, length,
extensions=self._extensions, predicates=self._extra_predicates, with_alignments=with_alignments)
matches = find_matches(
&self.patterns[0],
self.patterns.size(),
doclike,
length,
extensions=self._extensions,
predicates=self._extra_predicates,
with_alignments=with_alignments
)
final_matches = []
pairs_by_id = {}
# For each key, either add all matches, or only the filtered,
@ -289,9 +288,9 @@ cdef class Matcher:
memset(matched, 0, length * sizeof(matched[0]))
span_filter = self._filter.get(key)
if span_filter == "FIRST":
sorted_pairs = sorted(pairs, key=lambda x: (x[0], -x[1]), reverse=False) # sort by start
sorted_pairs = sorted(pairs, key=lambda x: (x[0], -x[1]), reverse=False) # sort by start
elif span_filter == "LONGEST":
sorted_pairs = sorted(pairs, key=lambda x: (x[1]-x[0], -x[0]), reverse=True) # reverse sort by length
sorted_pairs = sorted(pairs, key=lambda x: (x[1]-x[0], -x[0]), reverse=True) # reverse sort by length
else:
raise ValueError(Errors.E947.format(expected=["FIRST", "LONGEST"], arg=span_filter))
for match in sorted_pairs:
@ -366,7 +365,6 @@ cdef find_matches(TokenPatternC** patterns, int n, object doclike, int length, e
cdef vector[MatchC] matches
cdef vector[vector[MatchAlignmentC]] align_states
cdef vector[vector[MatchAlignmentC]] align_matches
cdef PatternStateC state
cdef int i, j, nr_extra_attr
cdef Pool mem = Pool()
output = []
@ -388,14 +386,22 @@ cdef find_matches(TokenPatternC** patterns, int n, object doclike, int length, e
value = token.vocab.strings[value]
extra_attr_values[i * nr_extra_attr + index] = value
# Main loop
cdef int nr_predicate = len(predicates)
for i in range(length):
for j in range(n):
states.push_back(PatternStateC(patterns[j], i, 0))
if with_alignments != 0:
align_states.resize(states.size())
transition_states(states, matches, align_states, align_matches, predicate_cache,
doclike[i], extra_attr_values, predicates, with_alignments)
transition_states(
states,
matches,
align_states,
align_matches,
predicate_cache,
doclike[i],
extra_attr_values,
predicates,
with_alignments
)
extra_attr_values += nr_extra_attr
predicate_cache += len(predicates)
# Handle matches that end in 0-width patterns
@ -421,18 +427,28 @@ cdef find_matches(TokenPatternC** patterns, int n, object doclike, int length, e
return output
cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& matches,
vector[vector[MatchAlignmentC]]& align_states, vector[vector[MatchAlignmentC]]& align_matches,
int8_t* cached_py_predicates,
Token token, const attr_t* extra_attrs, py_predicates, bint with_alignments) except *:
cdef void transition_states(
vector[PatternStateC]& states,
vector[MatchC]& matches,
vector[vector[MatchAlignmentC]]& align_states,
vector[vector[MatchAlignmentC]]& align_matches,
int8_t* cached_py_predicates,
Token token,
const attr_t* extra_attrs,
py_predicates,
bint with_alignments
) except *:
cdef int q = 0
cdef vector[PatternStateC] new_states
cdef vector[vector[MatchAlignmentC]] align_new_states
cdef int nr_predicate = len(py_predicates)
for i in range(states.size()):
if states[i].pattern.nr_py >= 1:
update_predicate_cache(cached_py_predicates,
states[i].pattern, token, py_predicates)
update_predicate_cache(
cached_py_predicates,
states[i].pattern,
token,
py_predicates
)
action = get_action(states[i], token.c, extra_attrs,
cached_py_predicates)
if action == REJECT:
@ -468,8 +484,12 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
align_new_states.push_back(align_states[q])
states[q].pattern += 1
if states[q].pattern.nr_py != 0:
update_predicate_cache(cached_py_predicates,
states[q].pattern, token, py_predicates)
update_predicate_cache(
cached_py_predicates,
states[q].pattern,
token,
py_predicates
)
action = get_action(states[q], token.c, extra_attrs,
cached_py_predicates)
# Update alignment before the transition of current state
@ -485,8 +505,12 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
ent_id = get_ent_id(state.pattern)
if action == MATCH:
matches.push_back(
MatchC(pattern_id=ent_id, start=state.start,
length=state.length+1))
MatchC(
pattern_id=ent_id,
start=state.start,
length=state.length+1
)
)
# `align_matches` always corresponds to `matches` 1:1
if with_alignments != 0:
align_matches.push_back(align_states[q])
@ -494,23 +518,35 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
# push match without last token if length > 0
if state.length > 0:
matches.push_back(
MatchC(pattern_id=ent_id, start=state.start,
length=state.length))
MatchC(
pattern_id=ent_id,
start=state.start,
length=state.length
)
)
# MATCH_DOUBLE emits matches twice,
# add one more to align_matches in order to keep 1:1 relationship
if with_alignments != 0:
align_matches.push_back(align_states[q])
# push match with last token
matches.push_back(
MatchC(pattern_id=ent_id, start=state.start,
length=state.length+1))
MatchC(
pattern_id=ent_id,
start=state.start,
length=state.length + 1
)
)
# `align_matches` always corresponds to `matches` 1:1
if with_alignments != 0:
align_matches.push_back(align_states[q])
elif action == MATCH_REJECT:
matches.push_back(
MatchC(pattern_id=ent_id, start=state.start,
length=state.length))
MatchC(
pattern_id=ent_id,
start=state.start,
length=state.length
)
)
# `align_matches` always corresponds to `matches` 1:1
if with_alignments != 0:
align_matches.push_back(align_states[q])
@ -533,8 +569,12 @@ cdef void transition_states(vector[PatternStateC]& states, vector[MatchC]& match
align_states.push_back(align_new_states[i])
cdef int update_predicate_cache(int8_t* cache,
const TokenPatternC* pattern, Token token, predicates) except -1:
cdef int update_predicate_cache(
int8_t* cache,
const TokenPatternC* pattern,
Token token,
predicates
) except -1:
# If the state references any extra predicates, check whether they match.
# These are cached, so that we don't call these potentially expensive
# Python functions more than we need to.
@ -580,10 +620,12 @@ cdef void finish_states(vector[MatchC]& matches, vector[PatternStateC]& states,
else:
state.pattern += 1
cdef action_t get_action(PatternStateC state,
const TokenC* token, const attr_t* extra_attrs,
const int8_t* predicate_matches) nogil:
cdef action_t get_action(
PatternStateC state,
const TokenC * token,
const attr_t * extra_attrs,
const int8_t * predicate_matches
) nogil:
"""We need to consider:
a) Does the token match the specification? [Yes, No]
b) What's the quantifier? [1, 0+, ?]
@ -649,53 +691,56 @@ cdef action_t get_action(PatternStateC state,
is_match = not is_match
quantifier = ONE
if quantifier == ONE:
if is_match and is_final:
# Yes, final: 1000
return MATCH
elif is_match and not is_final:
# Yes, non-final: 0100
return ADVANCE
elif not is_match and is_final:
# No, final: 0000
return REJECT
else:
return REJECT
if is_match and is_final:
# Yes, final: 1000
return MATCH
elif is_match and not is_final:
# Yes, non-final: 0100
return ADVANCE
elif not is_match and is_final:
# No, final: 0000
return REJECT
else:
return REJECT
elif quantifier == ZERO_PLUS:
if is_match and is_final:
# Yes, final: 1001
return MATCH_EXTEND
elif is_match and not is_final:
# Yes, non-final: 0011
return RETRY_EXTEND
elif not is_match and is_final:
# No, final 2000 (note: Don't include last token!)
return MATCH_REJECT
else:
# No, non-final 0010
return RETRY
if is_match and is_final:
# Yes, final: 1001
return MATCH_EXTEND
elif is_match and not is_final:
# Yes, non-final: 0011
return RETRY_EXTEND
elif not is_match and is_final:
# No, final 2000 (note: Don't include last token!)
return MATCH_REJECT
else:
# No, non-final 0010
return RETRY
elif quantifier == ZERO_ONE:
if is_match and is_final:
# Yes, final: 3000
# To cater for a pattern ending in "?", we need to add
# a match both with and without the last token
return MATCH_DOUBLE
elif is_match and not is_final:
# Yes, non-final: 0110
# We need both branches here, consider a pair like:
# pattern: .?b string: b
# If we 'ADVANCE' on the .?, we miss the match.
return RETRY_ADVANCE
elif not is_match and is_final:
# No, final 2000 (note: Don't include last token!)
return MATCH_REJECT
else:
# No, non-final 0010
return RETRY
if is_match and is_final:
# Yes, final: 3000
# To cater for a pattern ending in "?", we need to add
# a match both with and without the last token
return MATCH_DOUBLE
elif is_match and not is_final:
# Yes, non-final: 0110
# We need both branches here, consider a pair like:
# pattern: .?b string: b
# If we 'ADVANCE' on the .?, we miss the match.
return RETRY_ADVANCE
elif not is_match and is_final:
# No, final 2000 (note: Don't include last token!)
return MATCH_REJECT
else:
# No, non-final 0010
return RETRY
cdef int8_t get_is_match(PatternStateC state,
const TokenC* token, const attr_t* extra_attrs,
const int8_t* predicate_matches) nogil:
cdef int8_t get_is_match(
PatternStateC state,
const TokenC* token,
const attr_t* extra_attrs,
const int8_t* predicate_matches
) nogil:
for i in range(state.pattern.nr_py):
if predicate_matches[state.pattern.py_predicates[i]] == -1:
return 0
@ -860,7 +905,7 @@ class _FuzzyPredicate:
self.is_extension = is_extension
if self.predicate not in self.operators:
raise ValueError(Errors.E126.format(good=self.operators, bad=self.predicate))
fuzz = self.predicate[len("FUZZY"):] # number after prefix
fuzz = self.predicate[len("FUZZY"):] # number after prefix
self.fuzzy = int(fuzz) if fuzz else -1
self.fuzzy_compare = fuzzy_compare
self.key = _predicate_cache_key(self.attr, self.predicate, value, fuzzy=self.fuzzy)
@ -1082,7 +1127,7 @@ def _get_extra_predicates_dict(attr, value_dict, vocab, predicate_types,
elif cls == _FuzzyPredicate:
if isinstance(value, dict):
# add predicates inside fuzzy operator
fuzz = type_[len("FUZZY"):] # number after prefix
fuzz = type_[len("FUZZY"):] # number after prefix
fuzzy_val = int(fuzz) if fuzz else -1
output.extend(_get_extra_predicates_dict(attr, value, vocab, predicate_types,
extra_predicates, seen_predicates,
@ -1101,8 +1146,9 @@ def _get_extra_predicates_dict(attr, value_dict, vocab, predicate_types,
return output
def _get_extension_extra_predicates(spec, extra_predicates, predicate_types,
seen_predicates):
def _get_extension_extra_predicates(
spec, extra_predicates, predicate_types, seen_predicates
):
output = []
for attr, value in spec.items():
if isinstance(value, dict):
@ -1131,7 +1177,7 @@ def _get_operators(spec):
return (ONE,)
elif spec["OP"] in lookup:
return lookup[spec["OP"]]
#Min_max {n,m}
# Min_max {n,m}
elif spec["OP"].startswith("{") and spec["OP"].endswith("}"):
# {n} --> {n,n} exactly n ONE,(n)
# {n,m}--> {n,m} min of n, max of m ONE,(n),ZERO_ONE,(m)
@ -1142,8 +1188,8 @@ def _get_operators(spec):
min_max = min_max if "," in min_max else f"{min_max},{min_max}"
n, m = min_max.split(",")
#1. Either n or m is a blank string and the other is numeric -->isdigit
#2. Both are numeric and n <= m
# 1. Either n or m is a blank string and the other is numeric -->isdigit
# 2. Both are numeric and n <= m
if (not n.isdecimal() and not m.isdecimal()) or (n.isdecimal() and m.isdecimal() and int(n) > int(m)):
keys = ", ".join(lookup.keys()) + ", {n}, {n,m}, {n,}, {,m} where n and m are integers and n <= m "
raise ValueError(Errors.E011.format(op=spec["OP"], opts=keys))

4
spacy/matcher/phrasematcher.pyx
View File

@ -1,14 +1,12 @@
# cython: infer_types=True, profile=True
from libc.stdint cimport uintptr_t
from preshed.maps cimport map_clear, map_get, map_init, map_iter, map_set
import warnings
from ..attrs cimport DEP, LEMMA, MORPH, ORTH, POS, TAG
from ..attrs cimport DEP, LEMMA, MORPH, POS, TAG
from ..attrs import IDS
from ..structs cimport TokenC
from ..tokens.span cimport Span
from ..tokens.token cimport Token
from ..typedefs cimport attr_t

17
spacy/ml/parser_model.pxd
View File

@ -40,11 +40,16 @@ cdef ActivationsC alloc_activations(SizesC n) nogil
cdef void free_activations(const ActivationsC* A) nogil
cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
const WeightsC* W, SizesC n) nogil
cdef void predict_states(
CBlas cblas, ActivationsC* A, StateC** states, const WeightsC* W, SizesC n
) nogil
cdef int arg_max_if_valid(const weight_t* scores, const int* is_valid, int n) nogil
cdef void cpu_log_loss(float* d_scores,
const float* costs, const int* is_valid, const float* scores, int O) nogil
cdef void cpu_log_loss(
float* d_scores,
const float* costs,
const int* is_valid,
const float* scores,
int O
) nogil

129
spacy/ml/parser_model.pyx
View File

@ -8,13 +8,13 @@ from thinc.backends.linalg cimport Vec, VecVec
import numpy
import numpy.random
from thinc.api import CupyOps, Model, NumpyOps, get_ops
from thinc.api import CupyOps, Model, NumpyOps
from .. import util
from ..errors import Errors
from ..pipeline._parser_internals.stateclass cimport StateClass
from ..typedefs cimport class_t, hash_t, weight_t
from ..typedefs cimport weight_t
cdef WeightsC get_c_weights(model) except *:
@ -78,33 +78,48 @@ cdef void resize_activations(ActivationsC* A, SizesC n) nogil:
A.is_valid = <int*>calloc(n.states * n.classes, sizeof(A.is_valid[0]))
A._max_size = n.states
else:
A.token_ids = <int*>realloc(A.token_ids,
n.states * n.feats * sizeof(A.token_ids[0]))
A.scores = <float*>realloc(A.scores,
n.states * n.classes * sizeof(A.scores[0]))
A.unmaxed = <float*>realloc(A.unmaxed,
n.states * n.hiddens * n.pieces * sizeof(A.unmaxed[0]))
A.hiddens = <float*>realloc(A.hiddens,
n.states * n.hiddens * sizeof(A.hiddens[0]))
A.is_valid = <int*>realloc(A.is_valid,
n.states * n.classes * sizeof(A.is_valid[0]))
A.token_ids = <int*>realloc(
A.token_ids, n.states * n.feats * sizeof(A.token_ids[0])
)
A.scores = <float*>realloc(
A.scores, n.states * n.classes * sizeof(A.scores[0])
)
A.unmaxed = <float*>realloc(
A.unmaxed, n.states * n.hiddens * n.pieces * sizeof(A.unmaxed[0])
)
A.hiddens = <float*>realloc(
A.hiddens, n.states * n.hiddens * sizeof(A.hiddens[0])
)
A.is_valid = <int*>realloc(
A.is_valid, n.states * n.classes * sizeof(A.is_valid[0])
)
A._max_size = n.states
A._curr_size = n.states
cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
const WeightsC* W, SizesC n) nogil:
cdef double one = 1.0
cdef void predict_states(
CBlas cblas, ActivationsC* A, StateC** states, const WeightsC* W, SizesC n
) nogil:
resize_activations(A, n)
for i in range(n.states):
states[i].set_context_tokens(&A.token_ids[i*n.feats], n.feats)
memset(A.unmaxed, 0, n.states * n.hiddens * n.pieces * sizeof(float))
memset(A.hiddens, 0, n.states * n.hiddens * sizeof(float))
sum_state_features(cblas, A.unmaxed,
W.feat_weights, A.token_ids, n.states, n.feats, n.hiddens * n.pieces)
sum_state_features(
cblas,
A.unmaxed,
W.feat_weights,
A.token_ids,
n.states,
n.feats,
n.hiddens * n.pieces
)
for i in range(n.states):
VecVec.add_i(&A.unmaxed[i*n.hiddens*n.pieces],
W.feat_bias, 1., n.hiddens * n.pieces)
VecVec.add_i(
&A.unmaxed[i*n.hiddens*n.pieces],
W.feat_bias, 1.,
n.hiddens * n.pieces
)
for j in range(n.hiddens):
index = i * n.hiddens * n.pieces + j * n.pieces
which = Vec.arg_max(&A.unmaxed[index], n.pieces)
@ -114,14 +129,15 @@ cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
memcpy(A.scores, A.hiddens, n.states * n.classes * sizeof(float))
else:
# Compute hidden-to-output
sgemm(cblas)(False, True, n.states, n.classes, n.hiddens,
sgemm(cblas)(
False, True, n.states, n.classes, n.hiddens,
1.0, <const float *>A.hiddens, n.hiddens,
<const float *>W.hidden_weights, n.hiddens,
0.0, A.scores, n.classes)
0.0, A.scores, n.classes
)
# Add bias
for i in range(n.states):
VecVec.add_i(&A.scores[i*n.classes],
W.hidden_bias, 1., n.classes)
VecVec.add_i(&A.scores[i*n.classes], W.hidden_bias, 1., n.classes)
# Set unseen classes to minimum value
i = 0
min_ = A.scores[0]
@ -134,9 +150,16 @@ cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
A.scores[i*n.classes+j] = min_
cdef void sum_state_features(CBlas cblas, float* output,
const float* cached, const int* token_ids, int B, int F, int O) nogil:
cdef int idx, b, f, i
cdef void sum_state_features(
CBlas cblas,
float* output,
const float* cached,
const int* token_ids,
int B,
int F,
int O
) nogil:
cdef int idx, b, f
cdef const float* feature
padding = cached
cached += F * O
@ -153,9 +176,13 @@ cdef void sum_state_features(CBlas cblas, float* output,
token_ids += F
cdef void cpu_log_loss(float* d_scores,
const float* costs, const int* is_valid, const float* scores,
int O) nogil:
cdef void cpu_log_loss(
float* d_scores,
const float* costs,
const int* is_valid,
const float* scores,
int O
) nogil:
"""Do multi-label log loss"""
cdef double max_, gmax, Z, gZ
best = arg_max_if_gold(scores, costs, is_valid, O)
@ -179,8 +206,9 @@ cdef void cpu_log_loss(float* d_scores,
d_scores[i] = exp(scores[i]-max_) / Z
cdef int arg_max_if_gold(const weight_t* scores, const weight_t* costs,
const int* is_valid, int n) nogil:
cdef int arg_max_if_gold(
const weight_t* scores, const weight_t* costs, const int* is_valid, int n
) nogil:
# Find minimum cost
cdef float cost = 1
for i in range(n):
@ -204,10 +232,17 @@ cdef int arg_max_if_valid(const weight_t* scores, const int* is_valid, int n) no
return best
class ParserStepModel(Model):
def __init__(self, docs, layers, *, has_upper, unseen_classes=None, train=True,
dropout=0.1):
def __init__(
self,
docs,
layers,
*,
has_upper,
unseen_classes=None,
train=True,
dropout=0.1
):
Model.__init__(self, name="parser_step_model", forward=step_forward)
self.attrs["has_upper"] = has_upper
self.attrs["dropout_rate"] = dropout
@ -268,8 +303,10 @@ class ParserStepModel(Model):
return ids
def backprop_step(self, token_ids, d_vector, get_d_tokvecs):
if isinstance(self.state2vec.ops, CupyOps) \
and not isinstance(token_ids, self.state2vec.ops.xp.ndarray):
if (
isinstance(self.state2vec.ops, CupyOps)
and not isinstance(token_ids, self.state2vec.ops.xp.ndarray)
):
# Move token_ids and d_vector to GPU, asynchronously
self.backprops.append((
util.get_async(self.cuda_stream, token_ids),
@ -279,7 +316,6 @@ class ParserStepModel(Model):
else:
self.backprops.append((token_ids, d_vector, get_d_tokvecs))
def finish_steps(self, golds):
# Add a padding vector to the d_tokvecs gradient, so that missing
# values don't affect the real gradient.
@ -292,14 +328,15 @@ class ParserStepModel(Model):
ids = ids.flatten()
d_state_features = d_state_features.reshape(
(ids.size, d_state_features.shape[2]))
self.ops.scatter_add(d_tokvecs, ids,
d_state_features)
self.ops.scatter_add(d_tokvecs, ids, d_state_features)
# Padded -- see update()
self.bp_tokvecs(d_tokvecs[:-1])
return d_tokvecs
NUMPY_OPS = NumpyOps()
def step_forward(model: ParserStepModel, states, is_train):
token_ids = model.get_token_ids(states)
vector, get_d_tokvecs = model.state2vec(token_ids, is_train)
@ -312,7 +349,7 @@ def step_forward(model: ParserStepModel, states, is_train):
scores, get_d_vector = model.vec2scores(vector, is_train)
else:
scores = NumpyOps().asarray(vector)
get_d_vector = lambda d_scores: d_scores
get_d_vector = lambda d_scores: d_scores # no-cython-lint: E731
# If the class is unseen, make sure its score is minimum
scores[:, model._class_mask == 0] = numpy.nanmin(scores)
@ -448,9 +485,11 @@ cdef class precompute_hiddens:
feat_weights = self.get_feat_weights()
cdef int[:, ::1] ids = token_ids
sum_state_features(cblas, <float*>state_vector.data,
feat_weights, &ids[0,0],
token_ids.shape[0], self.nF, self.nO*self.nP)
sum_state_features(
cblas, <float*>state_vector.data,
feat_weights, &ids[0, 0],
token_ids.shape[0], self.nF, self.nO*self.nP
)
state_vector += self.bias
state_vector, bp_nonlinearity = self._nonlinearity(state_vector)
@ -475,7 +514,7 @@ cdef class precompute_hiddens:
def backprop_maxout(d_best):
return self.ops.backprop_maxout(d_best, mask, self.nP)
return state_vector, backprop_maxout
def _relu_nonlinearity(self, state_vector):
@ -489,5 +528,5 @@ cdef class precompute_hiddens:
def backprop_relu(d_best):
d_best *= mask
return d_best.reshape((d_best.shape + (1,)))
return state_vector, backprop_relu

8
spacy/morphology.pxd
View File

@ -11,7 +11,7 @@ from .typedefs cimport attr_t, hash_t
cdef class Morphology:
cdef readonly Pool mem
cdef readonly StringStore strings
cdef PreshMap tags # Keyed by hash, value is pointer to tag
cdef PreshMap tags # Keyed by hash, value is pointer to tag
cdef MorphAnalysisC create_morph_tag(self, field_feature_pairs) except *
cdef int insert(self, MorphAnalysisC tag) except -1
@ -20,4 +20,8 @@ cdef class Morphology:
cdef int check_feature(const MorphAnalysisC* morph, attr_t feature) nogil
cdef list list_features(const MorphAnalysisC* morph)
cdef np.ndarray get_by_field(const MorphAnalysisC* morph, attr_t field)
cdef int get_n_by_field(attr_t* results, const MorphAnalysisC* morph, attr_t field) nogil
cdef int get_n_by_field(
attr_t* results,
const MorphAnalysisC* morph,
attr_t field,
) nogil

10
spacy/morphology.pyx
View File

@ -83,10 +83,11 @@ cdef class Morphology:
features = self.normalize_attrs(features)
string_features = {self.strings.as_string(field): self.strings.as_string(values) for field, values in features.items()}
# normalized UFEATS string with sorted fields and values
norm_feats_string = self.FEATURE_SEP.join(sorted([
self.FIELD_SEP.join([field, values])
for field, values in string_features.items()
]))
norm_feats_string = self.FEATURE_SEP.join(
sorted(
[self.FIELD_SEP.join([field, values]) for field, values in string_features.items()]
)
)
return norm_feats_string or self.EMPTY_MORPH
def normalize_attrs(self, attrs):
@ -192,6 +193,7 @@ cdef int get_n_by_field(attr_t* results, const MorphAnalysisC* morph, attr_t fie
n_results += 1
return n_results
def unpickle_morphology(strings, tags):
cdef Morphology morphology = Morphology(strings)
for tag in tags:

2
spacy/parts_of_speech.pxd
View File

@ -8,7 +8,7 @@ cpdef enum univ_pos_t:
ADV
AUX
CONJ
CCONJ # U20
CCONJ # U20
DET
INTJ
NOUN

17
spacy/pipeline/_edit_tree_internals/edit_trees.pxd
View File

@ -46,11 +46,18 @@ cdef struct EditTreeC:
bint is_match_node
NodeC inner
cdef inline EditTreeC edittree_new_match(len_t prefix_len, len_t suffix_len,
uint32_t prefix_tree, uint32_t suffix_tree):
cdef MatchNodeC match_node = MatchNodeC(prefix_len=prefix_len,
suffix_len=suffix_len, prefix_tree=prefix_tree,
suffix_tree=suffix_tree)
cdef inline EditTreeC edittree_new_match(
len_t prefix_len,
len_t suffix_len,
uint32_t prefix_tree,
uint32_t suffix_tree
):
cdef MatchNodeC match_node = MatchNodeC(
prefix_len=prefix_len,
suffix_len=suffix_len,
prefix_tree=prefix_tree,
suffix_tree=suffix_tree
)
cdef NodeC inner = NodeC(match_node=match_node)
return EditTreeC(is_match_node=True, inner=inner)

14
spacy/pipeline/_edit_tree_internals/edit_trees.pyx
View File

@ -5,8 +5,6 @@ from libc.string cimport memset
from libcpp.pair cimport pair
from libcpp.vector cimport vector
from pathlib import Path
from ...typedefs cimport hash_t
from ... import util
@ -25,17 +23,16 @@ cdef LCS find_lcs(str source, str target):
target (str): The second string.
RETURNS (LCS): The spans of the longest common subsequences.
"""
cdef Py_ssize_t source_len = len(source)
cdef Py_ssize_t target_len = len(target)
cdef size_t longest_align = 0;
cdef size_t longest_align = 0
cdef int source_idx, target_idx
cdef LCS lcs
cdef Py_UCS4 source_cp, target_cp
memset(&lcs, 0, sizeof(lcs))
cdef vector[size_t] prev_aligns = vector[size_t](target_len);
cdef vector[size_t] cur_aligns = vector[size_t](target_len);
cdef vector[size_t] prev_aligns = vector[size_t](target_len)
cdef vector[size_t] cur_aligns = vector[size_t](target_len)
for (source_idx, source_cp) in enumerate(source):
for (target_idx, target_cp) in enumerate(target):
@ -89,7 +86,7 @@ cdef class EditTrees:
cdef LCS lcs = find_lcs(form, lemma)
cdef EditTreeC tree
cdef uint32_t tree_id, prefix_tree, suffix_tree
cdef uint32_t prefix_tree, suffix_tree
if lcs_is_empty(lcs):
tree = edittree_new_subst(self.strings.add(form), self.strings.add(lemma))
else:
@ -108,7 +105,7 @@ cdef class EditTrees:
return self._tree_id(tree)
cdef uint32_t _tree_id(self, EditTreeC tree):
# If this tree has been constructed before, return its identifier.
# If this tree has been constructed before, return its identifier.
cdef hash_t hash = edittree_hash(tree)
cdef unordered_map[hash_t, uint32_t].iterator iter = self.map.find(hash)
if iter != self.map.end():
@ -289,6 +286,7 @@ def _tree2dict(tree):
tree = tree["inner"]["subst_node"]
return(dict(tree))
def _dict2tree(tree):
errors = validate_edit_tree(tree)
if errors:

6
spacy/pipeline/_parser_internals/_beam_utils.pyx
View File

@ -1,17 +1,14 @@
# cython: infer_types=True
# cython: profile=True
cimport numpy as np
import numpy
from cpython.ref cimport Py_XDECREF, PyObject
from thinc.extra.search cimport Beam
from thinc.extra.search import MaxViolation
from thinc.extra.search cimport MaxViolation
from ...typedefs cimport class_t, hash_t
from ...typedefs cimport class_t
from .transition_system cimport Transition, TransitionSystem
from ...errors import Errors
@ -146,7 +143,6 @@ def update_beam(TransitionSystem moves, states, golds, model, int width, beam_de
cdef MaxViolation violn
pbeam = BeamBatch(moves, states, golds, width=width, density=beam_density)
gbeam = BeamBatch(moves, states, golds, width=width, density=0.0)
cdef StateClass state
beam_maps = []
backprops = []
violns = [MaxViolation() for _ in range(len(states))]

1
spacy/pipeline/_parser_internals/_state.pxd
View File

@ -277,7 +277,6 @@ cdef cppclass StateC:
return n
int n_L(int head) nogil const:
return n_arcs(this._left_arcs, head)

18
spacy/pipeline/_parser_internals/arc_eager.pyx
View File

@ -9,7 +9,7 @@ from ...strings cimport hash_string
from ...structs cimport TokenC
from ...tokens.doc cimport Doc, set_children_from_heads
from ...tokens.token cimport MISSING_DEP
from ...typedefs cimport attr_t, hash_t
from ...typedefs cimport attr_t
from ...training import split_bilu_label
@ -68,8 +68,9 @@ cdef struct GoldParseStateC:
weight_t pop_cost
cdef GoldParseStateC create_gold_state(Pool mem, const StateC* state,
heads, labels, sent_starts) except *:
cdef GoldParseStateC create_gold_state(
Pool mem, const StateC* state, heads, labels, sent_starts
) except *:
cdef GoldParseStateC gs
gs.length = len(heads)
gs.stride = 1
@ -82,7 +83,7 @@ cdef GoldParseStateC create_gold_state(Pool mem, const StateC* state,
gs.n_kids_in_stack = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids_in_stack[0]))
for i, is_sent_start in enumerate(sent_starts):
if is_sent_start == True:
if is_sent_start is True:
gs.state_bits[i] = set_state_flag(
gs.state_bits[i],
IS_SENT_START,
@ -210,6 +211,7 @@ cdef class ArcEagerGold:
def update(self, StateClass stcls):
update_gold_state(&self.c, stcls.c)
def _get_aligned_sent_starts(example):
"""Get list of SENT_START attributes aligned to the predicted tokenization.
If the reference has not sentence starts, return a list of None values.
@ -524,7 +526,6 @@ cdef class Break:
"""
@staticmethod
cdef bint is_valid(const StateC* st, attr_t label) nogil:
cdef int i
if st.buffer_length() < 2:
return False
elif st.B(1) != st.B(0) + 1:
@ -556,8 +557,8 @@ cdef class Break:
cost -= 1
if gold.heads[si] == b0:
cost -= 1
if not is_sent_start(gold, state.B(1)) \
and not is_sent_start_unknown(gold, state.B(1)):
if not is_sent_start(gold, state.B(1)) and\
not is_sent_start_unknown(gold, state.B(1)):
cost += 1
return cost
@ -803,7 +804,6 @@ cdef class ArcEager(TransitionSystem):
raise TypeError(Errors.E909.format(name="ArcEagerGold"))
cdef ArcEagerGold gold_ = gold
gold_state = gold_.c
n_gold = 0
if self.c[i].is_valid(stcls.c, self.c[i].label):
cost = self.c[i].get_cost(stcls.c, &gold_state, self.c[i].label)
else:
@ -875,7 +875,7 @@ cdef class ArcEager(TransitionSystem):
print("Gold")
for token in example.y:
print(token.i, token.text, token.dep_, token.head.text)
aligned_heads, aligned_labels = example.get_aligned_parse()
aligned_heads, _aligned_labels = example.get_aligned_parse()
print("Aligned heads")
for i, head in enumerate(aligned_heads):
print(example.x[i], example.x[head] if head is not None else "__")

17
spacy/pipeline/_parser_internals/ner.pyx
View File

@ -1,6 +1,3 @@
import os
import random
from cymem.cymem cimport Pool
from libc.stdint cimport int32_t
@ -14,7 +11,7 @@ from ...tokens.span import Span
from ...attrs cimport IS_SPACE
from ...lexeme cimport Lexeme
from ...structs cimport SpanC, TokenC
from ...structs cimport SpanC
from ...tokens.span cimport Span
from ...typedefs cimport attr_t, weight_t
@ -141,11 +138,10 @@ cdef class BiluoPushDown(TransitionSystem):
OUT: Counter()
}
actions[OUT][''] = 1 # Represents a token predicted to be outside of any entity
actions[UNIT][''] = 1 # Represents a token prohibited to be in an entity
actions[UNIT][''] = 1 # Represents a token prohibited to be in an entity
for entity_type in kwargs.get('entity_types', []):
for action in (BEGIN, IN, LAST, UNIT):
actions[action][entity_type] = 1
moves = ('M', 'B', 'I', 'L', 'U')
for example in kwargs.get('examples', []):
for token in example.y:
ent_type = token.ent_type_
@ -164,7 +160,7 @@ cdef class BiluoPushDown(TransitionSystem):
if token.ent_type:
labels.add(token.ent_type_)
return labels
def move_name(self, int move, attr_t label):
if move == OUT:
return 'O'
@ -325,7 +321,6 @@ cdef class BiluoPushDown(TransitionSystem):
raise TypeError(Errors.E909.format(name="BiluoGold"))
cdef BiluoGold gold_ = gold
gold_state = gold_.c
n_gold = 0
if self.c[i].is_valid(stcls.c, self.c[i].label):
cost = self.c[i].get_cost(stcls.c, &gold_state, self.c[i].label)
else:
@ -486,10 +481,8 @@ cdef class In:
@staticmethod
cdef weight_t cost(const StateC* s, const void* _gold, attr_t label) nogil:
gold = <GoldNERStateC*>_gold
move = IN
cdef int next_act = gold.ner[s.B(1)].move if s.B(1) >= 0 else OUT
cdef int g_act = gold.ner[s.B(0)].move
cdef attr_t g_tag = gold.ner[s.B(0)].label
cdef bint is_sunk = _entity_is_sunk(s, gold.ner)
if g_act == MISSING:
@ -549,12 +542,10 @@ cdef class Last:
@staticmethod
cdef weight_t cost(const StateC* s, const void* _gold, attr_t label) nogil:
gold = <GoldNERStateC*>_gold
move = LAST
b0 = s.B(0)
ent_start = s.E(0)
cdef int g_act = gold.ner[b0].move
cdef attr_t g_tag = gold.ner[b0].label
cdef int cost = 0
@ -650,7 +641,6 @@ cdef class Unit:
cost += 1
break
return cost
cdef class Out:
@ -675,7 +665,6 @@ cdef class Out:
cdef weight_t cost(const StateC* s, const void* _gold, attr_t label) nogil:
gold = <GoldNERStateC*>_gold
cdef int g_act = gold.ner[s.B(0)].move
cdef attr_t g_tag = gold.ner[s.B(0)].label
cdef weight_t cost = 0
if g_act == MISSING:
pass

12
spacy/pipeline/_parser_internals/nonproj.pyx
View File

@ -125,14 +125,17 @@ def decompose(label):
def is_decorated(label):
return DELIMITER in label
def count_decorated_labels(gold_data):
freqs = {}
for example in gold_data:
proj_heads, deco_deps = projectivize(example.get_aligned("HEAD"),
example.get_aligned("DEP"))
# set the label to ROOT for each root dependent
deco_deps = ['ROOT' if head == i else deco_deps[i]
for i, head in enumerate(proj_heads)]
deco_deps = [
'ROOT' if head == i else deco_deps[i]
for i, head in enumerate(proj_heads)
]
# count label frequencies
for label in deco_deps:
if is_decorated(label):
@ -160,9 +163,9 @@ def projectivize(heads, labels):
cdef vector[int] _heads_to_c(heads):
cdef vector[int] c_heads;
cdef vector[int] c_heads
for head in heads:
if head == None:
if head is None:
c_heads.push_back(-1)
else:
assert head < len(heads)
@ -199,6 +202,7 @@ def _decorate(heads, proj_heads, labels):
deco_labels.append(labels[tokenid])
return deco_labels
def get_smallest_nonproj_arc_slow(heads):
cdef vector[int] c_heads = _heads_to_c(heads)
return _get_smallest_nonproj_arc(c_heads)

24
spacy/pipeline/_parser_internals/stateclass.pyx
View File

@ -1,6 +1,4 @@
# cython: infer_types=True
import numpy
from libcpp.vector cimport vector
from ...tokens.doc cimport Doc
@ -38,11 +36,11 @@ cdef class StateClass:
cdef vector[ArcC] arcs
self.c.get_arcs(&arcs)
return list(arcs)
#py_arcs = []
#for arc in arcs:
# if arc.head != -1 and arc.child != -1:
# py_arcs.append((arc.head, arc.child, arc.label))
#return arcs
# py_arcs = []
# for arc in arcs:
# if arc.head != -1 and arc.child != -1:
# py_arcs.append((arc.head, arc.child, arc.label))
# return arcs
def add_arc(self, int head, int child, int label):
self.c.add_arc(head, child, label)
@ -52,10 +50,10 @@ cdef class StateClass:
def H(self, int child):
return self.c.H(child)
def L(self, int head, int idx):
return self.c.L(head, idx)
def R(self, int head, int idx):
return self.c.R(head, idx)
@ -98,7 +96,7 @@ cdef class StateClass:
def H(self, int i):
return self.c.H(i)
def E(self, int i):
return self.c.E(i)
@ -116,7 +114,7 @@ cdef class StateClass:
def H_(self, int i):
return self.doc[self.c.H(i)]
def E_(self, int i):
return self.doc[self.c.E(i)]
@ -125,7 +123,7 @@ cdef class StateClass:
def R_(self, int i, int idx):
return self.doc[self.c.R(i, idx)]
def empty(self):
return self.c.empty()
@ -134,7 +132,7 @@ cdef class StateClass:
def at_break(self):
return False
#return self.c.at_break()
# return self.c.at_break()
def has_head(self, int i):
return self.c.has_head(i)

14
spacy/pipeline/_parser_internals/transition_system.pxd
View File

@ -20,11 +20,15 @@ cdef struct Transition:
int (*do)(StateC* state, attr_t label) nogil
ctypedef weight_t (*get_cost_func_t)(const StateC* state, const void* gold,
attr_tlabel) nogil
ctypedef weight_t (*move_cost_func_t)(const StateC* state, const void* gold) nogil
ctypedef weight_t (*label_cost_func_t)(const StateC* state, const void*
gold, attr_t label) nogil
ctypedef weight_t (*get_cost_func_t)(
const StateC* state, const void* gold, attr_tlabel
) nogil
ctypedef weight_t (*move_cost_func_t)(
const StateC* state, const void* gold
) nogil
ctypedef weight_t (*label_cost_func_t)(
const StateC* state, const void* gold, attr_t label
) nogil
ctypedef int (*do_func_t)(StateC* state, attr_t label) nogil

3
spacy/pipeline/_parser_internals/transition_system.pyx
View File

@ -8,9 +8,7 @@ from collections import Counter
import srsly
from ...structs cimport TokenC
from ...tokens.doc cimport Doc
from ...typedefs cimport attr_t, weight_t
from . cimport _beam_utils
from .stateclass cimport StateClass
from ... import util
@ -231,7 +229,6 @@ cdef class TransitionSystem:
return self
def to_bytes(self, exclude=tuple()):
transitions = []
serializers = {
'moves': lambda: srsly.json_dumps(self.labels),
'strings': lambda: self.strings.to_bytes(),

3
spacy/pipeline/dep_parser.pyx
View File

@ -1,6 +1,6 @@
# cython: infer_types=True, profile=True, binding=True
from collections import defaultdict
from typing import Callable, Iterable, Optional
from typing import Callable, Optional
from thinc.api import Config, Model
@ -124,6 +124,7 @@ def make_parser(
scorer=scorer,
)
@Language.factory(
"beam_parser",
assigns=["token.dep", "token.head", "token.is_sent_start", "doc.sents"],

11
spacy/pipeline/morphologizer.pyx
View File

@ -2,7 +2,6 @@
from itertools import islice
from typing import Callable, Dict, Optional, Union
import srsly
from thinc.api import Config, Model, SequenceCategoricalCrossentropy
from ..morphology cimport Morphology
@ -14,10 +13,8 @@ from ..errors import Errors
from ..language import Language
from ..parts_of_speech import IDS as POS_IDS
from ..scorer import Scorer
from ..symbols import POS
from ..training import validate_examples, validate_get_examples
from ..util import registry
from .pipe import deserialize_config
from .tagger import Tagger
# See #9050
@ -76,8 +73,11 @@ def morphologizer_score(examples, **kwargs):
results = {}
results.update(Scorer.score_token_attr(examples, "pos", **kwargs))
results.update(Scorer.score_token_attr(examples, "morph", getter=morph_key_getter, **kwargs))
results.update(Scorer.score_token_attr_per_feat(examples,
"morph", getter=morph_key_getter, **kwargs))
results.update(
Scorer.score_token_attr_per_feat(
examples, "morph", getter=morph_key_getter, **kwargs
)
)
return results
@ -233,7 +233,6 @@ class Morphologizer(Tagger):
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
cdef Vocab vocab = self.vocab
cdef bint overwrite = self.cfg["overwrite"]
cdef bint extend = self.cfg["extend"]
labels = self.labels

9
spacy/pipeline/multitask.pyx
View File

@ -4,13 +4,10 @@ from typing import Optional
import numpy
from thinc.api import Config, CosineDistance, Model, set_dropout_rate, to_categorical
from ..tokens.doc cimport Doc
from ..attrs import ID, POS
from ..attrs import ID
from ..errors import Errors
from ..language import Language
from ..training import validate_examples
from ._parser_internals import nonproj
from .tagger import Tagger
from .trainable_pipe import TrainablePipe
@ -103,10 +100,9 @@ class MultitaskObjective(Tagger):
cdef int idx = 0
correct = numpy.zeros((scores.shape[0],), dtype="i")
guesses = scores.argmax(axis=1)
docs = [eg.predicted for eg in examples]
for i, eg in enumerate(examples):
# Handles alignment for tokenization differences
doc_annots = eg.get_aligned() # TODO
_doc_annots = eg.get_aligned() # TODO
for j in range(len(eg.predicted)):
tok_annots = {key: values[j] for key, values in tok_annots.items()}
label = self.make_label(j, tok_annots)
@ -206,7 +202,6 @@ class ClozeMultitask(TrainablePipe):
losses[self.name] = 0.
set_dropout_rate(self.model, drop)
validate_examples(examples, "ClozeMultitask.rehearse")
docs = [eg.predicted for eg in examples]
predictions, bp_predictions = self.model.begin_update()
loss, d_predictions = self.get_loss(examples, self.vocab.vectors.data, predictions)
bp_predictions(d_predictions)

5
spacy/pipeline/ner.pyx
View File

@ -1,6 +1,6 @@
# cython: infer_types=True, profile=True, binding=True
from collections import defaultdict
from typing import Callable, Iterable, Optional
from typing import Callable, Optional
from thinc.api import Config, Model
@ -10,7 +10,7 @@ from ._parser_internals.ner cimport BiluoPushDown
from .transition_parser cimport Parser
from ..language import Language
from ..scorer import PRFScore, get_ner_prf
from ..scorer import get_ner_prf
from ..training import remove_bilu_prefix
from ..util import registry
@ -100,6 +100,7 @@ def make_ner(
scorer=scorer,
)
@Language.factory(
"beam_ner",
assigns=["doc.ents", "token.ent_iob", "token.ent_type"],

6
spacy/pipeline/pipe.pyx
View File

@ -1,6 +1,6 @@
# cython: infer_types=True, profile=True, binding=True
import warnings
from typing import Callable, Dict, Iterable, Iterator, Optional, Tuple, Union
from typing import Callable, Dict, Iterable, Iterator, Tuple, Union
import srsly
@ -40,7 +40,7 @@ cdef class Pipe:
"""
raise NotImplementedError(Errors.E931.format(parent="Pipe", method="__call__", name=self.name))
def pipe(self, stream: Iterable[Doc], *, batch_size: int=128) -> Iterator[Doc]:
def pipe(self, stream: Iterable[Doc], *, batch_size: int = 128) -> Iterator[Doc]:
"""Apply the pipe to a stream of documents. This usually happens under
the hood when the nlp object is called on a text and all components are
applied to the Doc.
@ -59,7 +59,7 @@ cdef class Pipe:
except Exception as e:
error_handler(self.name, self, [doc], e)
def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language=None):
def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language = None):
"""Initialize the pipe. For non-trainable components, this method
is optional. For trainable components, which should inherit
from the subclass TrainablePipe, the provided data examples

28
spacy/pipeline/sentencizer.pyx
View File

@ -7,13 +7,13 @@ from ..tokens.doc cimport Doc
from .. import util
from ..language import Language
from ..scorer import Scorer
from .pipe import Pipe
from .senter import senter_score
# see #9050
BACKWARD_OVERWRITE = False
@Language.factory(
"sentencizer",
assigns=["token.is_sent_start", "doc.sents"],
@ -36,17 +36,19 @@ class Sentencizer(Pipe):
DOCS: https://spacy.io/api/sentencizer
"""
default_punct_chars = ['!', '.', '?', '։', '؟', '۔', '܀', '܁', '܂', '߹',
'।', '॥', '၊', '။', '።', '፧', '፨', '᙮', '᜵', '᜶', '᠃', '᠉', '᥄',
'᥅', '᪨', '᪩', '᪪', '᪫', '᭚', '᭛', '᭞', '᭟', '᰻', '᰼', '᱾', '᱿',
'‼', '‽', '⁇', '⁈', '⁉', '⸮', '⸼', '꓿', '꘎', '꘏', '꛳', '꛷', '꡶',
'꡷', '꣎', '꣏', '꤯', '꧈', '꧉', '꩝', '꩞', '꩟', '꫰', '꫱', '꯫', '﹒',
'﹖', '﹗', '！', '．', '？', '𐩖', '𐩗', '𑁇', '𑁈', '𑂾', '𑂿', '𑃀',
'𑃁', '𑅁', '𑅂', '𑅃', '𑇅', '𑇆', '𑇍', '𑇞', '𑇟', '𑈸', '𑈹', '𑈻', '𑈼',
'𑊩', '𑑋', '𑑌', '𑗂', '𑗃', '𑗉', '𑗊', '𑗋', '𑗌', '𑗍', '𑗎', '𑗏', '𑗐',
'𑗑', '𑗒', '𑗓', '𑗔', '𑗕', '𑗖', '𑗗', '𑙁', '𑙂', '𑜼', '𑜽', '𑜾', '𑩂',
'𑩃', '𑪛', '𑪜', '𑱁', '𑱂', '𖩮', '𖩯', '𖫵', '𖬷', '𖬸', '𖭄', '𛲟', '𝪈',
'｡', '。']
default_punct_chars = [
'!', '.', '?', '։', '؟', '۔', '܀', '܁', '܂', '߹',
'।', '॥', '၊', '။', '።', '፧', '፨', '᙮', '᜵', '᜶', '᠃', '᠉', '᥄',
'᥅', '᪨', '᪩', '᪪', '᪫', '᭚', '᭛', '᭞', '᭟', '᰻', '᰼', '᱾', '᱿',
'‼', '‽', '⁇', '⁈', '⁉', '⸮', '⸼', '꓿', '꘎', '꘏', '꛳', '꛷', '꡶',
'꡷', '꣎', '꣏', '꤯', '꧈', '꧉', '꩝', '꩞', '꩟', '꫰', '꫱', '꯫', '﹒',
'﹖', '﹗', '！', '．', '？', '𐩖', '𐩗', '𑁇', '𑁈', '𑂾', '𑂿', '𑃀',
'𑃁', '𑅁', '𑅂', '𑅃', '𑇅', '𑇆', '𑇍', '𑇞', '𑇟', '𑈸', '𑈹', '𑈻', '𑈼',
'𑊩', '𑑋', '𑑌', '𑗂', '𑗃', '𑗉', '𑗊', '𑗋', '𑗌', '𑗍', '𑗎', '𑗏', '𑗐',
'𑗑', '𑗒', '𑗓', '𑗔', '𑗕', '𑗖', '𑗗', '𑙁', '𑙂', '𑜼', '𑜽', '𑜾', '𑩂',
'𑩃', '𑪛', '𑪜', '𑱁', '𑱂', '𖩮', '𖩯', '𖫵', '𖬷', '𖬸', '𖭄', '𛲟', '𝪈',
'｡', '。'
]
def __init__(
self,
@ -128,7 +130,6 @@ class Sentencizer(Pipe):
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
cdef int idx = 0
for i, doc in enumerate(docs):
doc_tag_ids = batch_tag_ids[i]
for j, tag_id in enumerate(doc_tag_ids):
@ -169,7 +170,6 @@ class Sentencizer(Pipe):
path = path.with_suffix(".json")
srsly.write_json(path, {"punct_chars": list(self.punct_chars), "overwrite": self.overwrite})
def from_disk(self, path, *, exclude=tuple()):
"""Load the sentencizer from disk.

1
spacy/pipeline/senter.pyx
View File

@ -2,7 +2,6 @@
from itertools import islice
from typing import Callable, Optional
import srsly
from thinc.api import Config, Model, SequenceCategoricalCrossentropy
from ..tokens.doc cimport Doc

11
spacy/pipeline/tagger.pyx
View File

@ -1,26 +1,18 @@
# cython: infer_types=True, profile=True, binding=True
import warnings
from itertools import islice
from typing import Callable, Optional
import numpy
import srsly
from thinc.api import Config, Model, SequenceCategoricalCrossentropy, set_dropout_rate
from thinc.types import Floats2d
from ..morphology cimport Morphology
from ..tokens.doc cimport Doc
from ..vocab cimport Vocab
from .. import util
from ..attrs import ID, POS
from ..errors import Errors, Warnings
from ..errors import Errors
from ..language import Language
from ..parts_of_speech import X
from ..scorer import Scorer
from ..training import validate_examples, validate_get_examples
from ..util import registry
from .pipe import deserialize_config
from .trainable_pipe import TrainablePipe
# See #9050
@ -169,7 +161,6 @@ class Tagger(TrainablePipe):
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
cdef Vocab vocab = self.vocab
cdef bint overwrite = self.cfg["overwrite"]
labels = self.labels
for i, doc in enumerate(docs):

14
spacy/pipeline/trainable_pipe.pyx
View File

@ -55,7 +55,7 @@ cdef class TrainablePipe(Pipe):
except Exception as e:
error_handler(self.name, self, [doc], e)
def pipe(self, stream: Iterable[Doc], *, batch_size: int=128) -> Iterator[Doc]:
def pipe(self, stream: Iterable[Doc], *, batch_size: int = 128) -> Iterator[Doc]:
"""Apply the pipe to a stream of documents. This usually happens under
the hood when the nlp object is called on a text and all components are
applied to the Doc.
@ -102,9 +102,9 @@ cdef class TrainablePipe(Pipe):
def update(self,
examples: Iterable["Example"],
*,
drop: float=0.0,
sgd: Optimizer=None,
losses: Optional[Dict[str, float]]=None) -> Dict[str, float]:
drop: float = 0.0,
sgd: Optimizer = None,
losses: Optional[Dict[str, float]] = None) -> Dict[str, float]:
"""Learn from a batch of documents and gold-standard information,
updating the pipe's model. Delegates to predict and get_loss.
@ -138,8 +138,8 @@ cdef class TrainablePipe(Pipe):
def rehearse(self,
examples: Iterable[Example],
*,
sgd: Optimizer=None,
losses: Dict[str, float]=None,
sgd: Optimizer = None,
losses: Dict[str, float] = None,
**config) -> Dict[str, float]:
"""Perform a "rehearsal" update from a batch of data. Rehearsal updates
teach the current model to make predictions similar to an initial model,
@ -177,7 +177,7 @@ cdef class TrainablePipe(Pipe):
"""
return util.create_default_optimizer()
def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language=None):
def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language = None):
"""Initialize the pipe for training, using data examples if available.
This method needs to be implemented by each TrainablePipe component,
ensuring the internal model (if available) is initialized properly

18
spacy/pipeline/transition_parser.pxd
View File

@ -13,8 +13,18 @@ cdef class Parser(TrainablePipe):
cdef readonly TransitionSystem moves
cdef public object _multitasks
cdef void _parseC(self, CBlas cblas, StateC** states,
WeightsC weights, SizesC sizes) nogil
cdef void _parseC(
self,
CBlas cblas,
StateC** states,
WeightsC weights,
SizesC sizes
) nogil
cdef void c_transition_batch(self, StateC** states, const float* scores,
int nr_class, int batch_size) nogil
cdef void c_transition_batch(
self,
StateC** states,
const float* scores,
int nr_class,
int batch_size
) nogil

64
spacy/pipeline/transition_parser.pyx
View File

@ -7,20 +7,15 @@ from cymem.cymem cimport Pool
from itertools import islice
from libc.stdlib cimport calloc, free
from libc.string cimport memcpy, memset
from libc.string cimport memset
from libcpp.vector cimport vector
import random
import srsly
from thinc.api import CupyOps, NumpyOps, get_ops, set_dropout_rate
from thinc.extra.search cimport Beam
import warnings
import numpy
import numpy.random
import srsly
from thinc.api import CupyOps, NumpyOps, set_dropout_rate
from ..ml.parser_model cimport (
ActivationsC,
@ -42,7 +37,7 @@ from .trainable_pipe import TrainablePipe
from ._parser_internals cimport _beam_utils
from .. import util
from ..errors import Errors, Warnings
from ..errors import Errors
from ..training import validate_examples, validate_get_examples
from ._parser_internals import _beam_utils
@ -258,7 +253,6 @@ cdef class Parser(TrainablePipe):
except Exception as e:
error_handler(self.name, self, batch_in_order, e)
def predict(self, docs):
if isinstance(docs, Doc):
docs = [docs]
@ -300,8 +294,6 @@ cdef class Parser(TrainablePipe):
return batch
def beam_parse(self, docs, int beam_width, float drop=0., beam_density=0.):
cdef Beam beam
cdef Doc doc
self._ensure_labels_are_added(docs)
batch = _beam_utils.BeamBatch(
self.moves,
@ -321,16 +313,18 @@ cdef class Parser(TrainablePipe):
del model
return list(batch)
cdef void _parseC(self, CBlas cblas, StateC** states,
WeightsC weights, SizesC sizes) nogil:
cdef int i, j
cdef void _parseC(
self, CBlas cblas, StateC** states, WeightsC weights, SizesC sizes
) nogil:
cdef int i
cdef vector[StateC*] unfinished
cdef ActivationsC activations = alloc_activations(sizes)
while sizes.states >= 1:
predict_states(cblas, &activations, states, &weights, sizes)
# Validate actions, argmax, take action.
self.c_transition_batch(states,
activations.scores, sizes.classes, sizes.states)
self.c_transition_batch(
states, activations.scores, sizes.classes, sizes.states
)
for i in range(sizes.states):
if not states[i].is_final():
unfinished.push_back(states[i])
@ -342,7 +336,6 @@ cdef class Parser(TrainablePipe):
def set_annotations(self, docs, states_or_beams):
cdef StateClass state
cdef Beam beam
cdef Doc doc
states = _beam_utils.collect_states(states_or_beams, docs)
for i, (state, doc) in enumerate(zip(states, docs)):
@ -359,8 +352,13 @@ cdef class Parser(TrainablePipe):
self.c_transition_batch(&c_states[0], c_scores, scores.shape[1], scores.shape[0])
return [state for state in states if not state.c.is_final()]
cdef void c_transition_batch(self, StateC** states, const float* scores,
int nr_class, int batch_size) nogil:
cdef void c_transition_batch(
self,
StateC** states,
const float* scores,
int nr_class,
int batch_size
) nogil:
# n_moves should not be zero at this point, but make sure to avoid zero-length mem alloc
with gil:
assert self.moves.n_moves > 0, Errors.E924.format(name=self.name)
@ -380,7 +378,6 @@ cdef class Parser(TrainablePipe):
free(is_valid)
def update(self, examples, *, drop=0., sgd=None, losses=None):
cdef StateClass state
if losses is None:
losses = {}
losses.setdefault(self.name, 0.)
@ -419,8 +416,7 @@ cdef class Parser(TrainablePipe):
if not states:
return losses
model, backprop_tok2vec = self.model.begin_update([eg.x for eg in examples])
all_states = list(states)
states_golds = list(zip(states, golds))
n_moves = 0
while states_golds:
@ -500,8 +496,16 @@ cdef class Parser(TrainablePipe):
del tutor
return losses
def update_beam(self, examples, *, beam_width,
drop=0., sgd=None, losses=None, beam_density=0.0):
def update_beam(
self,
examples,
*,
beam_width,
drop=0.,
sgd=None,
losses=None,
beam_density=0.0
):
states, golds, _ = self.moves.init_gold_batch(examples)
if not states:
return losses
@ -531,8 +535,9 @@ cdef class Parser(TrainablePipe):
is_valid = <int*>mem.alloc(self.moves.n_moves, sizeof(int))
costs = <float*>mem.alloc(self.moves.n_moves, sizeof(float))
cdef np.ndarray d_scores = numpy.zeros((len(states), self.moves.n_moves),
dtype='f', order='C')
cdef np.ndarray d_scores = numpy.zeros(
(len(states), self.moves.n_moves), dtype='f', order='C'
)
c_d_scores = <float*>d_scores.data
unseen_classes = self.model.attrs["unseen_classes"]
for i, (state, gold) in enumerate(zip(states, golds)):
@ -542,8 +547,9 @@ cdef class Parser(TrainablePipe):
for j in range(self.moves.n_moves):
if costs[j] <= 0.0 and j in unseen_classes:
unseen_classes.remove(j)
cpu_log_loss(c_d_scores,
costs, is_valid, &scores[i, 0], d_scores.shape[1])
cpu_log_loss(
c_d_scores, costs, is_valid, &scores[i, 0], d_scores.shape[1]
)
c_d_scores += d_scores.shape[1]
# Note that we don't normalize this. See comment in update() for why.
if losses is not None:

5
spacy/strings.pyx
View File

@ -2,7 +2,6 @@
cimport cython
from libc.stdint cimport uint32_t
from libc.string cimport memcpy
from libcpp.set cimport set
from murmurhash.mrmr cimport hash32, hash64
import srsly
@ -20,9 +19,10 @@ cdef inline bint _try_coerce_to_hash(object key, hash_t* out_hash):
try:
out_hash[0] = key
return True
except:
except: # no-cython-lint
return False
def get_string_id(key):
"""Get a string ID, handling the reserved symbols correctly. If the key is
already an ID, return it.
@ -87,7 +87,6 @@ cdef Utf8Str* _allocate(Pool mem, const unsigned char* chars, uint32_t length) e
cdef int n_length_bytes
cdef int i
cdef Utf8Str* string = <Utf8Str*>mem.alloc(1, sizeof(Utf8Str))
cdef uint32_t ulength = length
if length < sizeof(string.s):
string.s[0] = <unsigned char>length
memcpy(&string.s[1], chars, length)

2
spacy/structs.pxd
View File

@ -52,7 +52,7 @@ cdef struct TokenC:
int sent_start
int ent_iob
attr_t ent_type # TODO: Is there a better way to do this? Multiple sources of truth..
attr_t ent_type # TODO: Is there a better way to do this? Multiple sources of truth..
attr_t ent_kb_id
hash_t ent_id

8
spacy/symbols.pxd
View File

@ -92,7 +92,7 @@ cdef enum symbol_t:
ADV
AUX
CONJ
CCONJ # U20
CCONJ # U20
DET
INTJ
NOUN
@ -418,7 +418,7 @@ cdef enum symbol_t:
ccomp
complm
conj
cop # U20
cop # U20
csubj
csubjpass
dep
@ -441,8 +441,8 @@ cdef enum symbol_t:
num
number
oprd
obj # U20
obl # U20
obj # U20
obl # U20
parataxis
partmod
pcomp

8
spacy/symbols.pyx
View File

@ -96,7 +96,7 @@ IDS = {
"ADV": ADV,
"AUX": AUX,
"CONJ": CONJ,
"CCONJ": CCONJ, # U20
"CCONJ": CCONJ, # U20
"DET": DET,
"INTJ": INTJ,
"NOUN": NOUN,
@ -421,7 +421,7 @@ IDS = {
"ccomp": ccomp,
"complm": complm,
"conj": conj,
"cop": cop, # U20
"cop": cop, # U20
"csubj": csubj,
"csubjpass": csubjpass,
"dep": dep,
@ -444,8 +444,8 @@ IDS = {
"num": num,
"number": number,
"oprd": oprd,
"obj": obj, # U20
"obl": obl, # U20
"obj": obj, # U20
"obl": obl, # U20
"parataxis": parataxis,
"partmod": partmod,
"pcomp": pcomp,

3
spacy/tests/matcher/test_pattern_validation.py
View File

@ -52,7 +52,8 @@ TEST_PATTERNS = [
@pytest.mark.parametrize(
"pattern", [[{"XX": "y"}, {"LENGTH": "2"}, {"TEXT": {"IN": 5}}]]
"pattern",
[[{"XX": "y"}], [{"LENGTH": "2"}], [{"TEXT": {"IN": 5}}], [{"text": {"in": 6}}]],
)
def test_matcher_pattern_validation(en_vocab, pattern):
matcher = Matcher(en_vocab, validate=True)

1
spacy/tests/package/test_requirements.py
View File

@ -12,6 +12,7 @@ def test_build_dependencies():
"flake8",
"hypothesis",
"pre-commit",
"cython-lint",
"black",
"isort",
"mypy",

19
spacy/tests/test_displacy.py
View File

@ -377,3 +377,22 @@ def test_displacy_manual_sorted_entities():
html = displacy.render(doc, style="ent", manual=True)
assert html.find("FIRST") < html.find("SECOND")
@pytest.mark.issue(12816)
def test_issue12816(en_vocab) -> None:
"""Test that displaCy's span visualizer escapes annotated HTML tags correctly."""
# Create a doc containing an annotated word and an unannotated HTML tag
doc = Doc(en_vocab, words=["test", "<TEST>"])
doc.spans["sc"] = [Span(doc, 0, 1, label="test")]
# Verify that the HTML tag is escaped when unannotated
html = displacy.render(doc, style="span")
assert "&lt;TEST&gt;" in html
# Annotate the HTML tag
doc.spans["sc"].append(Span(doc, 1, 2, label="test"))
# Verify that the HTML tag is still escaped
html = displacy.render(doc, style="span")
assert "&lt;TEST&gt;" in html

76
spacy/tokenizer.pxd
View File

@ -31,24 +31,58 @@ cdef class Tokenizer:
cdef Doc _tokenize_affixes(self, str string, bint with_special_cases)
cdef int _apply_special_cases(self, Doc doc) except -1
cdef void _filter_special_spans(self, vector[SpanC] &original,
vector[SpanC] &filtered, int doc_len) nogil
cdef object _prepare_special_spans(self, Doc doc,
vector[SpanC] &filtered)
cdef int _retokenize_special_spans(self, Doc doc, TokenC* tokens,
object span_data)
cdef int _try_specials_and_cache(self, hash_t key, Doc tokens,
int* has_special,
bint with_special_cases) except -1
cdef int _tokenize(self, Doc tokens, str span, hash_t key,
int* has_special, bint with_special_cases) except -1
cdef str _split_affixes(self, Pool mem, str string,
vector[LexemeC*] *prefixes,
vector[LexemeC*] *suffixes, int* has_special,
bint with_special_cases)
cdef int _attach_tokens(self, Doc tokens, str string,
vector[LexemeC*] *prefixes,
vector[LexemeC*] *suffixes, int* has_special,
bint with_special_cases) except -1
cdef int _save_cached(self, const TokenC* tokens, hash_t key,
int* has_special, int n) except -1
cdef void _filter_special_spans(
self,
vector[SpanC] &original,
vector[SpanC] &filtered,
int doc_len,
) nogil
cdef object _prepare_special_spans(
self,
Doc doc,
vector[SpanC] &filtered,
)
cdef int _retokenize_special_spans(
self,
Doc doc,
TokenC* tokens,
object span_data,
)
cdef int _try_specials_and_cache(
self,
hash_t key,
Doc tokens,
int* has_special,
bint with_special_cases,
) except -1
cdef int _tokenize(
self,
Doc tokens,
str span,
hash_t key,
int* has_special,
bint with_special_cases,
) except -1
cdef str _split_affixes(
self,
Pool mem,
str string,
vector[LexemeC*] *prefixes,
vector[LexemeC*] *suffixes, int* has_special,
bint with_special_cases,
)
cdef int _attach_tokens(
self,
Doc tokens,
str string,
vector[LexemeC*] *prefixes,
vector[LexemeC*] *suffixes, int* has_special,
bint with_special_cases,
) except -1
cdef int _save_cached(
self,
const TokenC* tokens,
hash_t key,
int* has_special,
int n,
) except -1

37
spacy/tokenizer.pyx
View File

@ -8,20 +8,18 @@ from libcpp.set cimport set as stdset
from preshed.maps cimport PreshMap
import re
import warnings
from .lexeme cimport EMPTY_LEXEME
from .strings cimport hash_string
from .tokens.doc cimport Doc
from . import util
from .attrs import intify_attrs
from .errors import Errors, Warnings
from .errors import Errors
from .scorer import Scorer
from .symbols import NORM, ORTH
from .tokens import Span
from .training import validate_examples
from .util import get_words_and_spaces, registry
from .util import get_words_and_spaces
cdef class Tokenizer:
@ -324,7 +322,7 @@ cdef class Tokenizer:
cdef int span_start
cdef int span_end
while i < doc.length:
if not i in span_data:
if i not in span_data:
tokens[i + offset] = doc.c[i]
i += 1
else:
@ -395,12 +393,15 @@ cdef class Tokenizer:
self._save_cached(&tokens.c[orig_size], orig_key, has_special,
tokens.length - orig_size)
cdef str _split_affixes(self, Pool mem, str string,
vector[const LexemeC*] *prefixes,
vector[const LexemeC*] *suffixes,
int* has_special,
bint with_special_cases):
cdef size_t i
cdef str _split_affixes(
self,
Pool mem,
str string,
vector[const LexemeC*] *prefixes,
vector[const LexemeC*] *suffixes,
int* has_special,
bint with_special_cases
):
cdef str prefix
cdef str suffix
cdef str minus_pre
@ -445,10 +446,6 @@ cdef class Tokenizer:
vector[const LexemeC*] *suffixes,
int* has_special,
bint with_special_cases) except -1:
cdef bint specials_hit = 0
cdef bint cache_hit = 0
cdef int split, end
cdef const LexemeC* const* lexemes
cdef const LexemeC* lexeme
cdef str span
cdef int i
@ -458,9 +455,11 @@ cdef class Tokenizer:
if string:
if self._try_specials_and_cache(hash_string(string), tokens, has_special, with_special_cases):
pass
elif (self.token_match and self.token_match(string)) or \
(self.url_match and \
self.url_match(string)):
elif (
(self.token_match and self.token_match(string)) or
(self.url_match and self.url_match(string))
):
# We're always saying 'no' to spaces here -- the caller will
# fix up the outermost one, with reference to the original.
# See Issue #859
@ -821,7 +820,7 @@ cdef class Tokenizer:
self.infix_finditer = None
self.token_match = None
self.url_match = None
msg = util.from_bytes(bytes_data, deserializers, exclude)
util.from_bytes(bytes_data, deserializers, exclude)
if "prefix_search" in data and isinstance(data["prefix_search"], str):
self.prefix_search = re.compile(data["prefix_search"]).search
if "suffix_search" in data and isinstance(data["suffix_search"], str):

27
spacy/tokens/_retokenize.pyx
View File

@ -1,7 +1,6 @@
# cython: infer_types=True, bounds_check=False, profile=True
from cymem.cymem cimport Pool
from libc.stdlib cimport free, malloc
from libc.string cimport memcpy, memset
from libc.string cimport memset
import numpy
from thinc.api import get_array_module
@ -10,7 +9,7 @@ from ..attrs cimport MORPH, NORM
from ..lexeme cimport EMPTY_LEXEME, Lexeme
from ..structs cimport LexemeC, TokenC
from ..vocab cimport Vocab
from .doc cimport Doc, set_children_from_heads, token_by_end, token_by_start
from .doc cimport Doc, set_children_from_heads, token_by_start
from .span cimport Span
from .token cimport Token
@ -147,7 +146,7 @@ def _merge(Doc doc, merges):
syntactic root of the span.
RETURNS (Token): The first newly merged token.
"""
cdef int i, merge_index, start, end, token_index, current_span_index, current_offset, offset, span_index
cdef int i, merge_index, start, token_index, current_span_index, current_offset, offset, span_index
cdef Span span
cdef const LexemeC* lex
cdef TokenC* token
@ -165,7 +164,6 @@ def _merge(Doc doc, merges):
merges.sort(key=_get_start)
for merge_index, (span, attributes) in enumerate(merges):
start = span.start
end = span.end
spans.append(span)
# House the new merged token where it starts
token = &doc.c[start]
@ -203,8 +201,9 @@ def _merge(Doc doc, merges):
# for the merged region. To do this, we create a boolean array indicating
# whether the row is to be deleted, then use numpy.delete
if doc.tensor is not None and doc.tensor.size != 0:
doc.tensor = _resize_tensor(doc.tensor,
[(m[0].start, m[0].end) for m in merges])
doc.tensor = _resize_tensor(
doc.tensor, [(m[0].start, m[0].end) for m in merges]
)
# Memorize span roots and sets dependencies of the newly merged
# tokens to the dependencies of their roots.
span_roots = []
@ -267,11 +266,11 @@ def _merge(Doc doc, merges):
span_index += 1
if span_index < len(spans) and i == spans[span_index].start:
# First token in a span
doc.c[i - offset] = doc.c[i] # move token to its place
doc.c[i - offset] = doc.c[i] # move token to its place
offset += (spans[span_index].end - spans[span_index].start) - 1
in_span = True
if not in_span:
doc.c[i - offset] = doc.c[i] # move token to its place
doc.c[i - offset] = doc.c[i] # move token to its place
for i in range(doc.length - offset, doc.length):
memset(&doc.c[i], 0, sizeof(TokenC))
@ -345,7 +344,11 @@ def _split(Doc doc, int token_index, orths, heads, attrs):
if to_process_tensor:
xp = get_array_module(doc.tensor)
if xp is numpy:
doc.tensor = xp.append(doc.tensor, xp.zeros((nb_subtokens,doc.tensor.shape[1]), dtype="float32"), axis=0)
doc.tensor = xp.append(
doc.tensor,
xp.zeros((nb_subtokens, doc.tensor.shape[1]), dtype="float32"),
axis=0
)
else:
shape = (doc.tensor.shape[0] + nb_subtokens, doc.tensor.shape[1])
resized_array = xp.zeros(shape, dtype="float32")
@ -367,7 +370,8 @@ def _split(Doc doc, int token_index, orths, heads, attrs):
token.norm = 0 # reset norm
if to_process_tensor:
# setting the tensors of the split tokens to array of zeros
doc.tensor[token_index + i:token_index + i + 1] = xp.zeros((1,doc.tensor.shape[1]), dtype="float32")
doc.tensor[token_index + i:token_index + i + 1] = \
xp.zeros((1, doc.tensor.shape[1]), dtype="float32")
# Update the character offset of the subtokens
if i != 0:
token.idx = orig_token.idx + idx_offset
@ -455,7 +459,6 @@ def normalize_token_attrs(Vocab vocab, attrs):
def set_token_attrs(Token py_token, attrs):
cdef TokenC* token = py_token.c
cdef const LexemeC* lex = token.lex
cdef Doc doc = py_token.doc
# Assign attributes
for attr_name, attr_value in attrs.items():
if attr_name == "_": # Set extension attributes

3
spacy/tokens/doc.pxd
View File

@ -31,7 +31,7 @@ cdef int token_by_start(const TokenC* tokens, int length, int start_char) except
cdef int token_by_end(const TokenC* tokens, int length, int end_char) except -2
cdef int [:,:] _get_lca_matrix(Doc, int start, int end)
cdef int [:, :] _get_lca_matrix(Doc, int start, int end)
cdef class Doc:
@ -61,7 +61,6 @@ cdef class Doc:
cdef int length
cdef int max_length
cdef public object noun_chunks_iterator
cdef object __weakref__

32
spacy/tokens/doc.pyx
View File

@ -43,14 +43,13 @@ from ..attrs cimport (
attr_id_t,
)
from ..lexeme cimport EMPTY_LEXEME, Lexeme
from ..typedefs cimport attr_t, flags_t
from ..typedefs cimport attr_t
from .token cimport Token
from .. import parts_of_speech, schemas, util
from ..attrs import IDS, intify_attr
from ..compat import copy_reg, pickle
from ..compat import copy_reg
from ..errors import Errors, Warnings
from ..morphology import Morphology
from ..util import get_words_and_spaces
from ._retokenize import Retokenizer
from .underscore import Underscore, get_ext_args
@ -784,7 +783,7 @@ cdef class Doc:
# TODO:
# 1. Test basic data-driven ORTH gazetteer
# 2. Test more nuanced date and currency regex
cdef attr_t entity_type, kb_id, ent_id
cdef attr_t kb_id, ent_id
cdef int ent_start, ent_end
ent_spans = []
for ent_info in ents:
@ -987,7 +986,6 @@ cdef class Doc:
>>> np_array = doc.to_array([LOWER, POS, ENT_TYPE, IS_ALPHA])
"""
cdef int i, j
cdef attr_id_t feature
cdef np.ndarray[attr_t, ndim=2] output
# Handle scalar/list inputs of strings/ints for py_attr_ids
# See also #3064
@ -999,8 +997,10 @@ cdef class Doc:
py_attr_ids = [py_attr_ids]
# Allow strings, e.g. 'lemma' or 'LEMMA'
try:
py_attr_ids = [(IDS[id_.upper()] if hasattr(id_, "upper") else id_)
for id_ in py_attr_ids]
py_attr_ids = [
(IDS[id_.upper()] if hasattr(id_, "upper") else id_)
for id_ in py_attr_ids
]
except KeyError as msg:
keys = [k for k in IDS.keys() if not k.startswith("FLAG")]
raise KeyError(Errors.E983.format(dict="IDS", key=msg, keys=keys)) from None
@ -1030,8 +1030,6 @@ cdef class Doc:
DOCS: https://spacy.io/api/doc#count_by
"""
cdef int i
cdef attr_t attr
cdef size_t count
if counts is None:
counts = Counter()
@ -1093,7 +1091,6 @@ cdef class Doc:
cdef int i, col
cdef int32_t abs_head_index
cdef attr_id_t attr_id
cdef TokenC* tokens = self.c
cdef int length = len(array)
if length != len(self):
raise ValueError(Errors.E971.format(array_length=length, doc_length=len(self)))
@ -1225,7 +1222,7 @@ cdef class Doc:
span.label,
span.kb_id,
span.id,
span.text, # included as a check
span.text, # included as a check
))
char_offset += len(doc.text)
if len(doc) > 0 and ensure_whitespace and not doc[-1].is_space and not bool(doc[-1].whitespace_):
@ -1508,7 +1505,6 @@ cdef class Doc:
attributes are inherited from the syntactic root of the span.
RETURNS (Token): The first newly merged token.
"""
cdef str tag, lemma, ent_type
attr_len = len(attributes)
span_len = len(spans)
if not attr_len == span_len:
@ -1624,7 +1620,6 @@ cdef class Doc:
for token in char_span[1:]:
token.is_sent_start = False
for span_group in doc_json.get("spans", {}):
spans = []
for span in doc_json["spans"][span_group]:
@ -1656,7 +1651,7 @@ cdef class Doc:
start = token_by_char(self.c, self.length, token_data["start"])
value = token_data["value"]
self[start]._.set(token_attr, value)
for span_attr in doc_json.get("underscore_span", {}):
if not Span.has_extension(span_attr):
Span.set_extension(span_attr)
@ -1698,7 +1693,7 @@ cdef class Doc:
token_data["dep"] = token.dep_
token_data["head"] = token.head.i
data["tokens"].append(token_data)
if self.spans:
data["spans"] = {}
for span_group in self.spans:
@ -1769,7 +1764,6 @@ cdef class Doc:
output.fill(255)
cdef int i, j, start_idx, end_idx
cdef bytes byte_string
cdef unsigned char utf8_char
for i, byte_string in enumerate(byte_strings):
j = 0
start_idx = 0
@ -1822,8 +1816,6 @@ cdef int token_by_char(const TokenC* tokens, int length, int char_idx) except -2
cdef int set_children_from_heads(TokenC* tokens, int start, int end) except -1:
# note: end is exclusive
cdef TokenC* head
cdef TokenC* child
cdef int i
# Set number of left/right children to 0. We'll increment it in the loops.
for i in range(start, end):
@ -1923,7 +1915,7 @@ cdef int _get_tokens_lca(Token token_j, Token token_k):
return -1
cdef int [:,:] _get_lca_matrix(Doc doc, int start, int end):
cdef int [:, :] _get_lca_matrix(Doc doc, int start, int end):
"""Given a doc and a start and end position defining a set of contiguous
tokens within it, returns a matrix of Lowest Common Ancestors (LCA), where
LCA[i, j] is the index of the lowest common ancestor among token i and j.
@ -1936,7 +1928,7 @@ cdef int [:,:] _get_lca_matrix(Doc doc, int start, int end):
RETURNS (int [:, :]): memoryview of numpy.array[ndim=2, dtype=numpy.int32],
with shape (n, n), where n = len(doc).
"""
cdef int [:,:] lca_matrix
cdef int [:, :] lca_matrix
cdef int j, k
n_tokens= end - start
lca_mat = numpy.empty((n_tokens, n_tokens), dtype=numpy.int32)

53
spacy/tokens/graph.pyx
View File

@ -3,7 +3,7 @@ from typing import Generator, List, Tuple
cimport cython
from cython.operator cimport dereference
from libc.stdint cimport int32_t, int64_t
from libc.stdint cimport int32_t
from libcpp.pair cimport pair
from libcpp.unordered_map cimport unordered_map
from libcpp.unordered_set cimport unordered_set
@ -11,7 +11,6 @@ from libcpp.unordered_set cimport unordered_set
import weakref
from murmurhash.mrmr cimport hash64
from preshed.maps cimport map_get_unless_missing
from .. import Errors
@ -28,7 +27,7 @@ from .token import Token
cdef class Edge:
cdef readonly Graph graph
cdef readonly int i
def __init__(self, Graph graph, int i):
self.graph = graph
self.i = i
@ -44,7 +43,7 @@ cdef class Edge:
@property
def head(self) -> "Node":
return Node(self.graph, self.graph.c.edges[self.i].head)
@property
def tail(self) -> "Tail":
return Node(self.graph, self.graph.c.edges[self.i].tail)
@ -70,7 +69,7 @@ cdef class Node:
def __init__(self, Graph graph, int i):
"""A reference to a node of an annotation graph. Each node is made up of
an ordered set of zero or more token indices.
Node references are usually created by the Graph object itself, or from
the Node or Edge objects. You usually won't need to instantiate this
class yourself.
@ -109,13 +108,13 @@ cdef class Node:
@property
def is_none(self) -> bool:
"""Whether the node is a special value, indicating 'none'.
The NoneNode type is returned by the Graph, Edge and Node objects when
there is no match to a query. It has the same API as Node, but it always
returns NoneNode, NoneEdge or empty lists for its queries.
"""
return False
@property
def doc(self) -> "Doc":
"""The Doc object that the graph refers to."""
@ -130,19 +129,19 @@ cdef class Node:
def head(self, i=None, label=None) -> "Node":
"""Get the head of the first matching edge, searching by index, label,
both or neither.
For instance, `node.head(i=1)` will get the head of the second edge that
this node is a tail of. `node.head(i=1, label="ARG0")` will further
check that the second edge has the label `"ARG0"`.
If no matching node can be found, the graph's NoneNode is returned.
"""
return self.headed(i=i, label=label)
def tail(self, i=None, label=None) -> "Node":
"""Get the tail of the first matching edge, searching by index, label,
both or neither.
If no matching node can be found, the graph's NoneNode is returned.
"""
return self.tailed(i=i, label=label).tail
@ -171,7 +170,7 @@ cdef class Node:
cdef vector[int] edge_indices
self._find_edges(edge_indices, "head", label)
return [Node(self.graph, self.graph.c.edges[i].head) for i in edge_indices]
def tails(self, label=None) -> List["Node"]:
"""Find all matching tails of this node."""
cdef vector[int] edge_indices
@ -200,7 +199,7 @@ cdef class Node:
return NoneEdge(self.graph)
else:
return Edge(self.graph, idx)
def tailed(self, i=None, label=None) -> Edge:
"""Find the first matching edge tailed by this node.
If no matching edge can be found, the graph's NoneEdge is returned.
@ -283,7 +282,7 @@ cdef class NoneEdge(Edge):
def __init__(self, graph):
self.graph = graph
self.i = -1
@property
def doc(self) -> "Doc":
return self.graph.doc
@ -291,7 +290,7 @@ cdef class NoneEdge(Edge):
@property
def head(self) -> "NoneNode":
return NoneNode(self.graph)
@property
def tail(self) -> "NoneNode":
return NoneNode(self.graph)
@ -319,7 +318,7 @@ cdef class NoneNode(Node):
def __len__(self):
return 0
@property
def is_none(self):
return -1
@ -340,14 +339,14 @@ cdef class NoneNode(Node):
def walk_heads(self):
yield from []
def walk_tails(self):
yield from []
cdef class Graph:
"""A set of directed labelled relationships between sets of tokens.
EXAMPLE:
Construction 1
>>> graph = Graph(doc, name="srl")
@ -372,7 +371,9 @@ cdef class Graph:
>>> assert graph.has_node((0,))
>>> assert graph.has_edge((0,), (1,3), label="agent")
"""
def __init__(self, doc, *, name="", nodes=[], edges=[], labels=None, weights=None):
def __init__(
self, doc, *, name="", nodes=[], edges=[], labels=None, weights=None # no-cython-lint
):
"""Create a Graph object.
doc (Doc): The Doc object the graph will refer to.
@ -438,13 +439,11 @@ cdef class Graph:
def add_edge(self, head, tail, *, label="", weight=None) -> Edge:
"""Add an edge to the graph, connecting two groups of tokens.
If there is already an edge for the (head, tail, label) triple, it will
be returned, and no new edge will be created. The weight of the edge
will be updated if a weight is specified.
"""
label_hash = self.doc.vocab.strings.as_int(label)
weight_float = weight if weight is not None else 0.0
edge_index = add_edge(
&self.c,
EdgeC(
@ -478,11 +477,11 @@ cdef class Graph:
def has_edge(self, head, tail, label) -> bool:
"""Check whether a (head, tail, label) triple is an edge in the graph."""
return not self.get_edge(head, tail, label=label).is_none
def add_node(self, indices) -> Node:
"""Add a node to the graph and return it. Nodes refer to ordered sets
of token indices.
This method is idempotent: if there is already a node for the given
indices, it is returned without a new node being created.
"""
@ -510,7 +509,7 @@ cdef class Graph:
return NoneNode(self)
else:
return Node(self, node_index)
def has_node(self, tuple indices) -> bool:
"""Check whether the graph has a node for the given indices."""
return not self.get_node(indices).is_none
@ -570,7 +569,7 @@ cdef int add_node(GraphC* graph, vector[int32_t]& node) nogil:
graph.roots.insert(index)
graph.node_map.insert(pair[hash_t, int](key, index))
return index
cdef int get_node(const GraphC* graph, vector[int32_t] node) nogil:
key = hash64(&node[0], node.size() * sizeof(node[0]), 0)

1
spacy/tokens/morphanalysis.pyx
View File

@ -89,4 +89,3 @@ cdef class MorphAnalysis:
def __repr__(self):
return self.to_json()

9
spacy/tokens/span.pyx
View File

@ -1,5 +1,4 @@
cimport numpy as np
from libc.math cimport sqrt
import copy
import warnings
@ -10,11 +9,10 @@ from thinc.api import get_array_module
from ..attrs cimport *
from ..attrs cimport ORTH, attr_id_t
from ..lexeme cimport Lexeme
from ..parts_of_speech cimport univ_pos_t
from ..structs cimport LexemeC, TokenC
from ..structs cimport TokenC
from ..symbols cimport dep
from ..typedefs cimport attr_t, flags_t, hash_t
from .doc cimport _get_lca_matrix, get_token_attr, token_by_end, token_by_start
from ..typedefs cimport attr_t, hash_t
from .doc cimport _get_lca_matrix, get_token_attr
from .token cimport Token
from ..errors import Errors, Warnings
@ -595,7 +593,6 @@ cdef class Span:
"""
return "".join([t.text_with_ws for t in self])
@property
def noun_chunks(self):
"""Iterate over the base noun phrases in the span. Yields base

6
spacy/tokens/span_group.pyx
View File

@ -1,7 +1,7 @@
import struct
import weakref
from copy import deepcopy
from typing import TYPE_CHECKING, Iterable, Optional, Tuple, Union
from typing import Iterable, Optional, Union
import srsly
@ -34,7 +34,7 @@ cdef class SpanGroup:
DOCS: https://spacy.io/api/spangroup
"""
def __init__(self, doc, *, name="", attrs={}, spans=[]):
def __init__(self, doc, *, name="", attrs={}, spans=[]): # no-cython-lint
"""Create a SpanGroup.
doc (Doc): The reference Doc object.
@ -311,7 +311,7 @@ cdef class SpanGroup:
other_attrs = deepcopy(other_group.attrs)
span_group.attrs.update({
key: value for key, value in other_attrs.items() \
key: value for key, value in other_attrs.items()
if key not in span_group.attrs
})
if len(other_group):

4
spacy/tokens/token.pxd
View File

@ -26,7 +26,7 @@ cdef class Token:
cdef Token self = Token.__new__(Token, vocab, doc, offset)
return self
#cdef inline TokenC struct_from_attrs(Vocab vocab, attrs):
# cdef inline TokenC struct_from_attrs(Vocab vocab, attrs):
# cdef TokenC token
# attrs = normalize_attrs(attrs)
@ -98,12 +98,10 @@ cdef class Token:
elif feat_name == SENT_START:
token.sent_start = value
@staticmethod
cdef inline int missing_dep(const TokenC* token) nogil:
return token.dep == MISSING_DEP
@staticmethod
cdef inline int missing_head(const TokenC* token) nogil:
return Token.missing_dep(token)

8
spacy/tokens/token.pyx
View File

@ -1,13 +1,11 @@
# cython: infer_types=True
# Compiler crashes on memory view coercion without this. Should report bug.
cimport numpy as np
from cython.view cimport array as cvarray
np.import_array()
import warnings
import numpy
from thinc.api import get_array_module
from ..attrs cimport (
@ -238,7 +236,7 @@ cdef class Token:
result = xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm)
# ensure we get a scalar back (numpy does this automatically but cupy doesn't)
return result.item()
def has_morph(self):
"""Check whether the token has annotated morph information.
Return False when the morph annotation is unset/missing.
@ -545,9 +543,9 @@ cdef class Token:
def __get__(self):
if self.i + 1 == len(self.doc):
return True
elif self.doc[self.i+1].is_sent_start == None:
elif self.doc[self.i+1].is_sent_start is None:
return None
elif self.doc[self.i+1].is_sent_start == True:
elif self.doc[self.i+1].is_sent_start is True:
return True
else:
return False

12
spacy/training/align.pyx
View File

@ -37,10 +37,14 @@ def get_alignments(A: List[str], B: List[str]) -> Tuple[List[List[int]], List[Li
b2a.append(set())
# Process the alignment at the current position
if A[token_idx_a] == B[token_idx_b] and \
(char_idx_a == 0 or \
char_to_token_a[char_idx_a - 1] < token_idx_a) and \
(char_idx_b == 0 or \
char_to_token_b[char_idx_b - 1] < token_idx_b):
(
char_idx_a == 0 or
char_to_token_a[char_idx_a - 1] < token_idx_a
) and \
(
char_idx_b == 0 or
char_to_token_b[char_idx_b - 1] < token_idx_b
):
# Current tokens are identical and both character offsets are the
# start of a token (either at the beginning of the document or the
# previous character belongs to a different token)

15
spacy/training/example.pyx
View File

@ -1,4 +1,3 @@
import warnings
from collections.abc import Iterable as IterableInstance
import numpy
@ -31,9 +30,9 @@ cpdef Doc annotations_to_doc(vocab, tok_annot, doc_annot):
attrs, array = _annot2array(vocab, tok_annot, doc_annot)
output = Doc(vocab, words=tok_annot["ORTH"], spaces=tok_annot["SPACY"])
if "entities" in doc_annot:
_add_entities_to_doc(output, doc_annot["entities"])
_add_entities_to_doc(output, doc_annot["entities"])
if "spans" in doc_annot:
_add_spans_to_doc(output, doc_annot["spans"])
_add_spans_to_doc(output, doc_annot["spans"])
if array.size:
output = output.from_array(attrs, array)
# links are currently added with ENT_KB_ID on the token level
@ -161,7 +160,6 @@ cdef class Example:
self._y_sig = y_sig
return self._cached_alignment
def _get_aligned_vectorized(self, align, gold_values):
# Fast path for Doc attributes/fields that are predominantly a single value,
# i.e., TAG, POS, MORPH.
@ -204,7 +202,6 @@ cdef class Example:
return output.tolist()
def _get_aligned_non_vectorized(self, align, gold_values):
# Slower path for fields that return multiple values (resulting
# in ragged arrays that cannot be vectorized trivially).
@ -221,7 +218,6 @@ cdef class Example:
return output
def get_aligned(self, field, as_string=False):
"""Return an aligned array for a token attribute."""
align = self.alignment.x2y
@ -330,7 +326,7 @@ cdef class Example:
missing=None
)
# Now fill the tokens we can align to O.
O = 2 # I=1, O=2, B=3
O = 2 # I=1, O=2, B=3 # no-cython-lint: E741
for i, ent_iob in enumerate(self.get_aligned("ENT_IOB")):
if x_tags[i] is None:
if ent_iob == O:
@ -340,7 +336,7 @@ cdef class Example:
return x_ents, x_tags
def get_aligned_ner(self):
x_ents, x_tags = self.get_aligned_ents_and_ner()
_x_ents, x_tags = self.get_aligned_ents_and_ner()
return x_tags
def get_matching_ents(self, check_label=True):
@ -398,7 +394,6 @@ cdef class Example:
return span_dict
def _links_to_dict(self):
links = {}
for ent in self.reference.ents:
@ -589,6 +584,7 @@ def _fix_legacy_dict_data(example_dict):
"doc_annotation": doc_dict
}
def _has_field(annot, field):
if field not in annot:
return False
@ -625,6 +621,7 @@ def _parse_ner_tags(biluo_or_offsets, vocab, words, spaces):
ent_types.append("")
return ent_iobs, ent_types
def _parse_links(vocab, words, spaces, links):
reference = Doc(vocab, words=words, spaces=spaces)
starts = {token.idx: token.i for token in reference}

31
spacy/training/gold_io.pyx
View File

@ -1,4 +1,3 @@
import json
import warnings
import srsly
@ -6,7 +5,7 @@ import srsly
from .. import util
from ..errors import Warnings
from ..tokens import Doc
from .iob_utils import offsets_to_biluo_tags, tags_to_entities
from .iob_utils import offsets_to_biluo_tags
def docs_to_json(docs, doc_id=0, ner_missing_tag="O"):
@ -23,7 +22,13 @@ def docs_to_json(docs, doc_id=0, ner_missing_tag="O"):
json_doc = {"id": doc_id, "paragraphs": []}
for i, doc in enumerate(docs):
raw = None if doc.has_unknown_spaces else doc.text
json_para = {'raw': raw, "sentences": [], "cats": [], "entities": [], "links": []}
json_para = {
'raw': raw,
"sentences": [],
"cats": [],
"entities": [],
"links": []
}
for cat, val in doc.cats.items():
json_cat = {"label": cat, "value": val}
json_para["cats"].append(json_cat)
@ -35,13 +40,17 @@ def docs_to_json(docs, doc_id=0, ner_missing_tag="O"):
if ent.kb_id_:
link_dict = {(ent.start_char, ent.end_char): {ent.kb_id_: 1.0}}
json_para["links"].append(link_dict)
biluo_tags = offsets_to_biluo_tags(doc, json_para["entities"], missing=ner_missing_tag)
biluo_tags = offsets_to_biluo_tags(
doc, json_para["entities"], missing=ner_missing_tag
)
attrs = ("TAG", "POS", "MORPH", "LEMMA", "DEP", "ENT_IOB")
include_annotation = {attr: doc.has_annotation(attr) for attr in attrs}
for j, sent in enumerate(doc.sents):
json_sent = {"tokens": [], "brackets": []}
for token in sent:
json_token = {"id": token.i, "orth": token.text, "space": token.whitespace_}
json_token = {
"id": token.i, "orth": token.text, "space": token.whitespace_
}
if include_annotation["TAG"]:
json_token["tag"] = token.tag_
if include_annotation["POS"]:
@ -125,9 +134,14 @@ def json_to_annotations(doc):
else:
sent_starts.append(-1)
if "brackets" in sent:
brackets.extend((b["first"] + sent_start_i,
b["last"] + sent_start_i, b["label"])
for b in sent["brackets"])
brackets.extend(
(
b["first"] + sent_start_i,
b["last"] + sent_start_i,
b["label"]
)
for b in sent["brackets"]
)
example["token_annotation"] = dict(
ids=ids,
@ -160,6 +174,7 @@ def json_to_annotations(doc):
)
yield example
def json_iterate(bytes utf8_str):
# We should've made these files jsonl...But since we didn't, parse out
# the docs one-by-one to reduce memory usage.

32
spacy/vectors.pyx
View File

@ -1,10 +1,8 @@
cimport numpy as np
from cython.operator cimport dereference as deref
from libc.stdint cimport uint32_t, uint64_t
from libcpp.set cimport set as cppset
from murmurhash.mrmr cimport hash128_x64
import functools
import warnings
from enum import Enum
from typing import cast
@ -119,7 +117,7 @@ cdef class Vectors:
if self.mode == Mode.default:
if data is None:
if shape is None:
shape = (0,0)
shape = (0, 0)
ops = get_current_ops()
data = ops.xp.zeros(shape, dtype="f")
self._unset = cppset[int]({i for i in range(data.shape[0])})
@ -260,11 +258,10 @@ cdef class Vectors:
def __eq__(self, other):
# Check for equality, with faster checks first
return (
self.shape == other.shape
and self.key2row == other.key2row
and self.to_bytes(exclude=["strings"])
== other.to_bytes(exclude=["strings"])
)
self.shape == other.shape
and self.key2row == other.key2row
and self.to_bytes(exclude=["strings"]) == other.to_bytes(exclude=["strings"])
)
def resize(self, shape, inplace=False):
"""Resize the underlying vectors array. If inplace=True, the memory
@ -520,11 +517,12 @@ cdef class Vectors:
# vectors e.g. (10000, 300)
# sims e.g. (1024, 10000)
sims = xp.dot(batch, vectors.T)
best_rows[i:i+batch_size] = xp.argpartition(sims, -n, axis=1)[:,-n:]
scores[i:i+batch_size] = xp.partition(sims, -n, axis=1)[:,-n:]
best_rows[i:i+batch_size] = xp.argpartition(sims, -n, axis=1)[:, -n:]
scores[i:i+batch_size] = xp.partition(sims, -n, axis=1)[:, -n:]
if sort and n >= 2:
sorted_index = xp.arange(scores.shape[0])[:,None][i:i+batch_size],xp.argsort(scores[i:i+batch_size], axis=1)[:,::-1]
sorted_index = xp.arange(scores.shape[0])[:, None][i:i+batch_size], \
xp.argsort(scores[i:i+batch_size], axis=1)[:, ::-1]
scores[i:i+batch_size] = scores[sorted_index]
best_rows[i:i+batch_size] = best_rows[sorted_index]
@ -538,8 +536,12 @@ cdef class Vectors:
numpy_rows = get_current_ops().to_numpy(best_rows)
keys = xp.asarray(
[[row2key[row] for row in numpy_rows[i] if row in row2key]
for i in range(len(queries)) ], dtype="uint64")
[
[row2key[row] for row in numpy_rows[i] if row in row2key]
for i in range(len(queries))
],
dtype="uint64"
)
return (keys, best_rows, scores)
def to_ops(self, ops: Ops):
@ -582,9 +584,9 @@ cdef class Vectors:
"""
xp = get_array_module(self.data)
if xp is numpy:
save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False)
save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False) # no-cython-lint
else:
save_array = lambda arr, file_: xp.save(file_, arr)
save_array = lambda arr, file_: xp.save(file_, arr) # no-cython-lint
def save_vectors(path):
# the source of numpy.save indicates that the file object is closed after use.

2
spacy/vocab.pxd
View File

@ -32,7 +32,7 @@ cdef class Vocab:
cdef public object writing_system
cdef public object get_noun_chunks
cdef readonly int length
cdef public object _unused_object # TODO remove in v4, see #9150
cdef public object _unused_object # TODO remove in v4, see #9150
cdef public object lex_attr_getters
cdef public object cfg

23
spacy/vocab.pyx
View File

@ -1,6 +1,4 @@
# cython: profile=True
from libc.string cimport memcpy
import functools
import numpy
@ -19,7 +17,6 @@ from .errors import Errors
from .lang.lex_attrs import LEX_ATTRS, get_lang, is_stop
from .lang.norm_exceptions import BASE_NORMS
from .lookups import Lookups
from .util import registry
from .vectors import Mode as VectorsMode
from .vectors import Vectors
@ -51,9 +48,17 @@ cdef class Vocab:
DOCS: https://spacy.io/api/vocab
"""
def __init__(self, lex_attr_getters=None, strings=tuple(), lookups=None,
oov_prob=-20., vectors_name=None, writing_system={},
get_noun_chunks=None, **deprecated_kwargs):
def __init__(
self,
lex_attr_getters=None,
strings=tuple(),
lookups=None,
oov_prob=-20.,
vectors_name=None,
writing_system={}, # no-cython-lint
get_noun_chunks=None,
**deprecated_kwargs
):
"""Create the vocabulary.
lex_attr_getters (dict): A dictionary mapping attribute IDs to
@ -150,7 +155,6 @@ cdef class Vocab:
cdef LexemeC* lex
cdef hash_t key = self.strings[string]
lex = <LexemeC*>self._by_orth.get(key)
cdef size_t addr
if lex != NULL:
assert lex.orth in self.strings
if lex.orth != key:
@ -183,7 +187,7 @@ cdef class Vocab:
# of the doc ownership).
# TODO: Change the C API so that the mem isn't passed in here.
mem = self.mem
#if len(string) < 3 or self.length < 10000:
# if len(string) < 3 or self.length < 10000:
# mem = self.mem
cdef bint is_oov = mem is not self.mem
lex = <LexemeC*>mem.alloc(1, sizeof(LexemeC))
@ -463,7 +467,6 @@ cdef class Vocab:
self.lookups.get_table("lexeme_norm"),
)
def to_disk(self, path, *, exclude=tuple()):
"""Save the current state to a directory.
@ -476,7 +479,6 @@ cdef class Vocab:
path = util.ensure_path(path)
if not path.exists():
path.mkdir()
setters = ["strings", "vectors"]
if "strings" not in exclude:
self.strings.to_disk(path / "strings.json")
if "vectors" not in exclude:
@ -495,7 +497,6 @@ cdef class Vocab:
DOCS: https://spacy.io/api/vocab#to_disk
"""
path = util.ensure_path(path)
getters = ["strings", "vectors"]
if "strings" not in exclude:
self.strings.from_disk(path / "strings.json") # TODO: add exclude?
if "vectors" not in exclude:

2
website/docs/api/language.mdx
View File

@ -856,7 +856,7 @@ token-to-vector embedding component like [`Tok2Vec`](/api/tok2vec) or
training a pipeline with components sourced from an existing pipeline: if
multiple components (e.g. tagger, parser, NER) listen to the same
token-to-vector component, but some of them are frozen and not updated, their
performance may degrade significally as the token-to-vector component is updated
performance may degrade significantly as the token-to-vector component is updated
with new data. To prevent this, listeners can be replaced with a standalone
token-to-vector layer that is owned by the component and doesn't change if the
component isn't updated.

2
website/docs/api/spanfinder.mdx
View File

@ -60,7 +60,7 @@ architectures and their arguments and hyperparameters.
| `model` | A model instance that is given a list of documents and predicts a probability for each token. ~~Model[List[Doc], Floats2d]~~ |
| `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ |
| `threshold` | Minimum probability to consider a prediction positive. Defaults to `0.5`. ~~float~~ |
| `max_length` | Maximum length of the produced spans, defaults to `None` meaning unlimited length. ~~Optional[int]~~ |
| `max_length` | Maximum length of the produced spans, defaults to `25`. ~~Optional[int]~~ |
| `min_length` | Minimum length of the produced spans, defaults to `None` meaning shortest span length is 1. ~~Optional[int]~~ |
| `scorer` | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~ |

4
website/docs/usage/index.mdx
View File

@ -261,7 +261,7 @@ source code and recompiling frequently.
#### Visual Studio Code extension
![spaCy extension demo](/images/spacy-extension-demo.gif)
![spaCy extension demo](/images/spacy-extension-demo.gif)
The [spaCy VSCode Extension](https://github.com/explosion/spacy-vscode) provides
additional tooling and features for working with spaCy's config files. Version
@ -310,7 +310,7 @@ You can configure the build process with the following environment variables:
| Variable | Description |
| -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `SPACY_EXTRAS` | Additional Python packages to install alongside spaCy with optional version specifications. Should be a string that can be passed to `pip install`. See [`Makefile`](%%GITHUB_SPACY/Makefile) for defaults. |
| `PYVER` | The Python version to build against. This version needs to be available on your build and runtime machines. Defaults to `3.6`. |
| `PYVER` | The Python version to build against. This version needs to be available on your build and runtime machines. Defaults to `3.8`. |
| `WHEELHOUSE` | Directory to store the wheel files during compilation. Defaults to `./wheelhouse`. |
### Run tests {id="run-tests"}

6
website/docs/usage/linguistic-features.mdx
View File

@ -113,7 +113,7 @@ print(doc[2].morph) # 'Case=Nom|Person=2|PronType=Prs'
print(doc[2].pos_) # 'PRON'
```
## Lemmatization {id="lemmatization",model="lemmatizer",version="3"}
## Lemmatization {id="lemmatization",version="3"}
spaCy provides two pipeline components for lemmatization:
@ -170,7 +170,7 @@ nlp = spacy.blank("sv")
nlp.add_pipe("lemmatizer", config={"mode": "lookup"})
```
### Rule-based lemmatizer {id="lemmatizer-rule"}
### Rule-based lemmatizer {id="lemmatizer-rule",model="morphologizer"}
When training pipelines that include a component that assigns part-of-speech
tags (a morphologizer or a tagger with a [POS mapping](#mappings-exceptions)), a
@ -194,7 +194,7 @@ information, without consulting the context of the token. The rule-based
lemmatizer also accepts list-based exception files. For English, these are
acquired from [WordNet](https://wordnet.princeton.edu/).
### Trainable lemmatizer
### Trainable lemmatizer {id="lemmatizer-train",model="trainable_lemmatizer"}
The [`EditTreeLemmatizer`](/api/edittreelemmatizer) can learn form-to-lemma
transformations from a training corpus that includes lemma annotations. This

2
website/meta/site.json
View File

@ -27,7 +27,7 @@
"indexName": "spacy"
},
"binderUrl": "explosion/spacy-io-binder",
"binderVersion": "3.5",
"binderVersion": "3.6",
"sections": [
{ "id": "usage", "title": "Usage Documentation", "theme": "blue" },
{ "id": "models", "title": "Models Documentation", "theme": "blue" },