explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-03 19:08:06 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #10897 from adrianeboyd/chore/backports-v3.3.1

Browse Source 
Backports for v3.3.1
This commit is contained in:
Adriane Boyd 2022-06-02 21:07:31 +02:00 committed by GitHub
commit f2219b1fd8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
28 changed files with 2432 additions and 243 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -22,7 +22,7 @@ langcodes>=3.2.0,<4.0.0
# Official Python utilities
setuptools
packaging>=20.0
typing_extensions>=3.7.4.1,<4.0.0.0; python_version < "3.8"
typing_extensions>=3.7.4.1,<4.2.0; python_version < "3.8"
# Development dependencies
pre-commit>=2.13.0
cython>=0.25,<3.0

2
setup.cfg
View File

@ -62,7 +62,7 @@ install_requires =
# Official Python utilities
setuptools
packaging>=20.0
typing_extensions>=3.7.4,<4.0.0.0; python_version < "3.8"
typing_extensions>=3.7.4,<4.2.0; python_version < "3.8"
langcodes>=3.2.0,<4.0.0
[options.entry_points]

17
spacy/errors.py
View File

@ -200,6 +200,11 @@ class Warnings(metaclass=ErrorsWithCodes):
"for the corpora used to train the language. Please check "
"`nlp.meta[\"sources\"]` for any relevant links.")
W119 = ("Overriding pipe name in `config` is not supported. Ignoring override '{name_in_config}'.")
W120 = ("Unable to load all spans in Doc.spans: more than one span group "
"with the name '{group_name}' was found in the saved spans data. "
"Only the last span group will be loaded under "
"Doc.spans['{group_name}']. Skipping span group with values: "
"{group_values}")
class Errors(metaclass=ErrorsWithCodes):
@ -528,6 +533,8 @@ class Errors(metaclass=ErrorsWithCodes):
E202 = ("Unsupported {name} mode '{mode}'. Supported modes: {modes}.")
# New errors added in v3.x
E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "
"permit overlapping spans.")
E855 = ("Invalid {obj}: {obj} is not from the same doc.")
E856 = ("Error accessing span at position {i}: out of bounds in span group "
"of length {length}.")
@ -899,8 +906,8 @@ class Errors(metaclass=ErrorsWithCodes):
E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't "
"exist.")
E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler "
"patterns.")
E1024 = ("A pattern with {attr_type} '{label}' is not present in "
"'{component}' patterns.")
E1025 = ("Cannot intify the value '{value}' as an IOB string. The only "
"supported values are: 'I', 'O', 'B' and ''")
E1026 = ("Edit tree has an invalid format:\n{errors}")
@ -915,6 +922,12 @@ class Errors(metaclass=ErrorsWithCodes):
E1035 = ("Token index {i} out of bounds ({length})")
E1036 = ("Cannot index into NoneNode")
E1037 = ("Invalid attribute value '{attr}'.")
E1038 = ("Invalid JSON input: {message}")
E1039 = ("The {obj} start or end annotations (start: {start}, end: {end}) "
"could not be aligned to token boundaries.")
E1040 = ("Doc.from_json requires all tokens to have the same attributes. "
"Some tokens do not contain annotation for: {partial_attrs}")
E1041 = ("Expected a string, Doc, or bytes as input, but got: {type}")
# Deprecated model shortcuts, only used in errors and warnings

55
spacy/language.py
View File

@ -1090,16 +1090,21 @@ class Language:
)
return self.tokenizer(text)
def _ensure_doc(self, doc_like: Union[str, Doc]) -> Doc:
"""Create a Doc if need be, or raise an error if the input is not a Doc or a string."""
def _ensure_doc(self, doc_like: Union[str, Doc, bytes]) -> Doc:
"""Create a Doc if need be, or raise an error if the input is not
a Doc, string, or a byte array (generated by Doc.to_bytes())."""
if isinstance(doc_like, Doc):
return doc_like
if isinstance(doc_like, str):
return self.make_doc(doc_like)
raise ValueError(Errors.E866.format(type=type(doc_like)))
if isinstance(doc_like, bytes):
return Doc(self.vocab).from_bytes(doc_like)
raise ValueError(Errors.E1041.format(type=type(doc_like)))
def _ensure_doc_with_context(self, doc_like: Union[str, Doc], context: Any) -> Doc:
"""Create a Doc if need be and add as_tuples context, or raise an error if the input is not a Doc or a string."""
def _ensure_doc_with_context(
self, doc_like: Union[str, Doc, bytes], context: _AnyContext
) -> Doc:
"""Call _ensure_doc to generate a Doc and set its context object."""
doc = self._ensure_doc(doc_like)
doc._context = context
return doc
@ -1519,7 +1524,6 @@ class Language:
DOCS: https://spacy.io/api/language#pipe
"""
# Handle texts with context as tuples
if as_tuples:
texts = cast(Iterable[Tuple[Union[str, Doc], _AnyContext]], texts)
docs_with_contexts = (
@ -1597,8 +1601,21 @@ class Language:
n_process: int,
batch_size: int,
) -> Iterator[Doc]:
def prepare_input(
texts: Iterable[Union[str, Doc]]
) -> Iterable[Tuple[Union[str, bytes], _AnyContext]]:
# Serialize Doc inputs to bytes to avoid incurring pickling
# overhead when they are passed to child processes. Also yield
# any context objects they might have separately (as they are not serialized).
for doc_like in texts:
if isinstance(doc_like, Doc):
yield (doc_like.to_bytes(), cast(_AnyContext, doc_like._context))
else:
yield (doc_like, cast(_AnyContext, None))
serialized_texts_with_ctx = prepare_input(texts) # type: ignore
# raw_texts is used later to stop iteration.
texts, raw_texts = itertools.tee(texts)
texts, raw_texts = itertools.tee(serialized_texts_with_ctx) # type: ignore
# for sending texts to worker
texts_q: List[mp.Queue] = [mp.Queue() for _ in range(n_process)]
# for receiving byte-encoded docs from worker
@ -1618,7 +1635,13 @@ class Language:
procs = [
mp.Process(
target=_apply_pipes,
args=(self._ensure_doc, pipes, rch, sch, Underscore.get_state()),
args=(
self._ensure_doc_with_context,
pipes,
rch,
sch,
Underscore.get_state(),
),
)
for rch, sch in zip(texts_q, bytedocs_send_ch)
]
@ -1631,12 +1654,12 @@ class Language:
recv.recv() for recv in cycle(bytedocs_recv_ch)
)
try:
for i, (_, (byte_doc, byte_context, byte_error)) in enumerate(
for i, (_, (byte_doc, context, byte_error)) in enumerate(
zip(raw_texts, byte_tuples), 1
):
if byte_doc is not None:
doc = Doc(self.vocab).from_bytes(byte_doc)
doc._context = byte_context
doc._context = context
yield doc
elif byte_error is not None:
error = srsly.msgpack_loads(byte_error)
@ -2163,7 +2186,7 @@ def _copy_examples(examples: Iterable[Example]) -> List[Example]:
def _apply_pipes(
ensure_doc: Callable[[Union[str, Doc]], Doc],
ensure_doc: Callable[[Union[str, Doc, bytes], _AnyContext], Doc],
pipes: Iterable[Callable[..., Iterator[Doc]]],
receiver,
sender,
@ -2184,17 +2207,19 @@ def _apply_pipes(
Underscore.load_state(underscore_state)
while True:
try:
texts = receiver.get()
docs = (ensure_doc(text) for text in texts)
texts_with_ctx = receiver.get()
docs = (
ensure_doc(doc_like, context) for doc_like, context in texts_with_ctx
)
for pipe in pipes:
docs = pipe(docs) # type: ignore[arg-type, assignment]
# Connection does not accept unpickable objects, so send list.
byte_docs = [(doc.to_bytes(), doc._context, None) for doc in docs]
padding = [(None, None, None)] * (len(texts) - len(byte_docs))
padding = [(None, None, None)] * (len(texts_with_ctx) - len(byte_docs))
sender.send(byte_docs + padding) # type: ignore[operator]
except Exception:
error_msg = [(None, None, srsly.msgpack_dumps(traceback.format_exc()))]
padding = [(None, None, None)] * (len(texts) - 1)
padding = [(None, None, None)] * (len(texts_with_ctx) - 1)
sender.send(error_msg + padding)

2
spacy/pipeline/__init__.py
View File

@ -13,6 +13,7 @@ from .sentencizer import Sentencizer
from .tagger import Tagger
from .textcat import TextCategorizer
from .spancat import SpanCategorizer
from .span_ruler import SpanRuler
from .textcat_multilabel import MultiLabel_TextCategorizer
from .tok2vec import Tok2Vec
from .functions import merge_entities, merge_noun_chunks, merge_subtokens
@ -30,6 +31,7 @@ __all__ = [
"SentenceRecognizer",
"Sentencizer",
"SpanCategorizer",
"SpanRuler",
"Tagger",
"TextCategorizer",
"Tok2Vec",

9
spacy/pipeline/entityruler.py
View File

@ -182,10 +182,7 @@ class EntityRuler(Pipe):
if start not in seen_tokens and end - 1 not in seen_tokens:
if match_id in self._ent_ids:
label, ent_id = self._ent_ids[match_id]
span = Span(doc, start, end, label=label)
if ent_id:
for token in span:
token.ent_id_ = ent_id
span = Span(doc, start, end, label=label, span_id=ent_id)
else:
span = Span(doc, start, end, label=match_id)
new_entities.append(span)
@ -359,7 +356,9 @@ class EntityRuler(Pipe):
(label, eid) for (label, eid) in self._ent_ids.values() if eid == ent_id
]
if not label_id_pairs:
raise ValueError(Errors.E1024.format(ent_id=ent_id))
raise ValueError(
Errors.E1024.format(attr_type="ID", label=ent_id, component=self.name)
)
created_labels = [
self._create_label(label, eid) for (label, eid) in label_id_pairs
]

569
spacy/pipeline/span_ruler.py Normal file
View File

@ -0,0 +1,569 @@
from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable
from typing import Sequence, Set, cast
import warnings
from functools import partial
from pathlib import Path
import srsly
from .pipe import Pipe
from ..training import Example
from ..language import Language
from ..errors import Errors, Warnings
from ..util import ensure_path, SimpleFrozenList, registry
from ..tokens import Doc, Span
from ..scorer import Scorer
from ..matcher import Matcher, PhraseMatcher
from .. import util
PatternType = Dict[str, Union[str, List[Dict[str, Any]]]]
DEFAULT_SPANS_KEY = "ruler"
@Language.factory(
"future_entity_ruler",
assigns=["doc.ents"],
default_config={
"phrase_matcher_attr": None,
"validate": False,
"overwrite_ents": False,
"scorer": {"@scorers": "spacy.entity_ruler_scorer.v1"},
"ent_id_sep": "__unused__",
},
default_score_weights={
"ents_f": 1.0,
"ents_p": 0.0,
"ents_r": 0.0,
"ents_per_type": None,
},
)
def make_entity_ruler(
nlp: Language,
name: str,
phrase_matcher_attr: Optional[Union[int, str]],
validate: bool,
overwrite_ents: bool,
scorer: Optional[Callable],
ent_id_sep: str,
):
if overwrite_ents:
ents_filter = prioritize_new_ents_filter
else:
ents_filter = prioritize_existing_ents_filter
return SpanRuler(
nlp,
name,
spans_key=None,
spans_filter=None,
annotate_ents=True,
ents_filter=ents_filter,
phrase_matcher_attr=phrase_matcher_attr,
validate=validate,
overwrite=False,
scorer=scorer,
)
@Language.factory(
"span_ruler",
assigns=["doc.spans"],
default_config={
"spans_key": DEFAULT_SPANS_KEY,
"spans_filter": None,
"annotate_ents": False,
"ents_filter": {"@misc": "spacy.first_longest_spans_filter.v1"},
"phrase_matcher_attr": None,
"validate": False,
"overwrite": True,
"scorer": {
"@scorers": "spacy.overlapping_labeled_spans_scorer.v1",
"spans_key": DEFAULT_SPANS_KEY,
},
},
default_score_weights={
f"spans_{DEFAULT_SPANS_KEY}_f": 1.0,
f"spans_{DEFAULT_SPANS_KEY}_p": 0.0,
f"spans_{DEFAULT_SPANS_KEY}_r": 0.0,
f"spans_{DEFAULT_SPANS_KEY}_per_type": None,
},
)
def make_span_ruler(
nlp: Language,
name: str,
spans_key: Optional[str],
spans_filter: Optional[Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]]],
annotate_ents: bool,
ents_filter: Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]],
phrase_matcher_attr: Optional[Union[int, str]],
validate: bool,
overwrite: bool,
scorer: Optional[Callable],
):
return SpanRuler(
nlp,
name,
spans_key=spans_key,
spans_filter=spans_filter,
annotate_ents=annotate_ents,
ents_filter=ents_filter,
phrase_matcher_attr=phrase_matcher_attr,
validate=validate,
overwrite=overwrite,
scorer=scorer,
)
def prioritize_new_ents_filter(
entities: Iterable[Span], spans: Iterable[Span]
) -> List[Span]:
"""Merge entities and spans into one list without overlaps by allowing
spans to overwrite any entities that they overlap with. Intended to
replicate the overwrite_ents=True behavior from the EntityRuler.
entities (Iterable[Span]): The entities, already filtered for overlaps.
spans (Iterable[Span]): The spans to merge, may contain overlaps.
RETURNS (List[Span]): Filtered list of non-overlapping spans.
"""
get_sort_key = lambda span: (span.end - span.start, -span.start)
spans = sorted(spans, key=get_sort_key, reverse=True)
entities = list(entities)
new_entities = []
seen_tokens: Set[int] = set()
for span in spans:
start = span.start
end = span.end
if all(token.i not in seen_tokens for token in span):
new_entities.append(span)
entities = [e for e in entities if not (e.start < end and e.end > start)]
seen_tokens.update(range(start, end))
return entities + new_entities
@registry.misc("spacy.prioritize_new_ents_filter.v1")
def make_prioritize_new_ents_filter():
return prioritize_new_ents_filter
def prioritize_existing_ents_filter(
entities: Iterable[Span], spans: Iterable[Span]
) -> List[Span]:
"""Merge entities and spans into one list without overlaps by prioritizing
existing entities. Intended to replicate the overwrite_ents=False behavior
from the EntityRuler.
entities (Iterable[Span]): The entities, already filtered for overlaps.
spans (Iterable[Span]): The spans to merge, may contain overlaps.
RETURNS (List[Span]): Filtered list of non-overlapping spans.
"""
get_sort_key = lambda span: (span.end - span.start, -span.start)
spans = sorted(spans, key=get_sort_key, reverse=True)
entities = list(entities)
new_entities = []
seen_tokens: Set[int] = set()
seen_tokens.update(*(range(ent.start, ent.end) for ent in entities))
for span in spans:
start = span.start
end = span.end
if all(token.i not in seen_tokens for token in span):
new_entities.append(span)
seen_tokens.update(range(start, end))
return entities + new_entities
@registry.misc("spacy.prioritize_existing_ents_filter.v1")
def make_preverse_existing_ents_filter():
return prioritize_existing_ents_filter
def overlapping_labeled_spans_score(
examples: Iterable[Example], *, spans_key=DEFAULT_SPANS_KEY, **kwargs
) -> Dict[str, Any]:
kwargs = dict(kwargs)
attr_prefix = f"spans_"
kwargs.setdefault("attr", f"{attr_prefix}{spans_key}")
kwargs.setdefault("allow_overlap", True)
kwargs.setdefault("labeled", True)
kwargs.setdefault(
"getter", lambda doc, key: doc.spans.get(key[len(attr_prefix) :], [])
)
kwargs.setdefault("has_annotation", lambda doc: spans_key in doc.spans)
return Scorer.score_spans(examples, **kwargs)
@registry.scorers("spacy.overlapping_labeled_spans_scorer.v1")
def make_overlapping_labeled_spans_scorer(spans_key: str = DEFAULT_SPANS_KEY):
return partial(overlapping_labeled_spans_score, spans_key=spans_key)
class SpanRuler(Pipe):
"""The SpanRuler lets you add spans to the `Doc.spans` using token-based
rules or exact phrase matches.
DOCS: https://spacy.io/api/spanruler
USAGE: https://spacy.io/usage/rule-based-matching#spanruler
"""
def __init__(
self,
nlp: Language,
name: str = "span_ruler",
*,
spans_key: Optional[str] = DEFAULT_SPANS_KEY,
spans_filter: Optional[
Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]]
] = None,
annotate_ents: bool = False,
ents_filter: Callable[
[Iterable[Span], Iterable[Span]], Iterable[Span]
] = util.filter_chain_spans,
phrase_matcher_attr: Optional[Union[int, str]] = None,
validate: bool = False,
overwrite: bool = False,
scorer: Optional[Callable] = partial(
overlapping_labeled_spans_score, spans_key=DEFAULT_SPANS_KEY
),
) -> None:
"""Initialize the span ruler. If patterns are supplied here, they
need to be a list of dictionaries with a `"label"` and `"pattern"`
key. A pattern can either be a token pattern (list) or a phrase pattern
(string). For example: `{'label': 'ORG', 'pattern': 'Apple'}`.
nlp (Language): The shared nlp object to pass the vocab to the matchers
and process phrase patterns.
name (str): Instance name of the current pipeline component. Typically
passed in automatically from the factory when the component is
added. Used to disable the current span ruler while creating
phrase patterns with the nlp object.
spans_key (Optional[str]): The spans key to save the spans under. If
`None`, no spans are saved. Defaults to "ruler".
spans_filter (Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]):
The optional method to filter spans before they are assigned to
doc.spans. Defaults to `None`.
annotate_ents (bool): Whether to save spans to doc.ents. Defaults to
`False`.
ents_filter (Callable[[Iterable[Span], Iterable[Span]], List[Span]]):
The method to filter spans before they are assigned to doc.ents.
Defaults to `util.filter_chain_spans`.
phrase_matcher_attr (Optional[Union[int, str]]): Token attribute to
match on, passed to the internal PhraseMatcher as `attr`. Defaults
to `None`.
validate (bool): Whether patterns should be validated, passed to
Matcher and PhraseMatcher as `validate`.
overwrite (bool): Whether to remove any existing spans under this spans
key if `spans_key` is set, and/or to remove any ents under `doc.ents` if
`annotate_ents` is set. Defaults to `True`.
scorer (Optional[Callable]): The scoring method. Defaults to
spacy.pipeline.span_ruler.overlapping_labeled_spans_score.
DOCS: https://spacy.io/api/spanruler#init
"""
self.nlp = nlp
self.name = name
self.spans_key = spans_key
self.annotate_ents = annotate_ents
self.phrase_matcher_attr = phrase_matcher_attr
self.validate = validate
self.overwrite = overwrite
self.spans_filter = spans_filter
self.ents_filter = ents_filter
self.scorer = scorer
self._match_label_id_map: Dict[int, Dict[str, str]] = {}
self.clear()
def __len__(self) -> int:
"""The number of all labels added to the span ruler."""
return len(self._patterns)
def __contains__(self, label: str) -> bool:
"""Whether a label is present in the patterns."""
for label_id in self._match_label_id_map.values():
if label_id["label"] == label:
return True
return False
@property
def key(self) -> Optional[str]:
"""Key of the doc.spans dict to save the spans under."""
return self.spans_key
def __call__(self, doc: Doc) -> Doc:
"""Find matches in document and add them as entities.
doc (Doc): The Doc object in the pipeline.
RETURNS (Doc): The Doc with added entities, if available.
DOCS: https://spacy.io/api/spanruler#call
"""
error_handler = self.get_error_handler()
try:
matches = self.match(doc)
self.set_annotations(doc, matches)
return doc
except Exception as e:
return error_handler(self.name, self, [doc], e)
def match(self, doc: Doc):
self._require_patterns()
with warnings.catch_warnings():
warnings.filterwarnings("ignore", message="\\[W036")
matches = cast(
List[Tuple[int, int, int]],
list(self.matcher(doc)) + list(self.phrase_matcher(doc)),
)
deduplicated_matches = set(
Span(
doc,
start,
end,
label=self._match_label_id_map[m_id]["label"],
span_id=self._match_label_id_map[m_id]["id"],
)
for m_id, start, end in matches
if start != end
)
return sorted(list(deduplicated_matches))
def set_annotations(self, doc, matches):
"""Modify the document in place"""
# set doc.spans if spans_key is set
if self.key:
spans = []
if self.key in doc.spans and not self.overwrite:
spans = doc.spans[self.key]
spans.extend(
self.spans_filter(spans, matches) if self.spans_filter else matches
)
doc.spans[self.key] = spans
# set doc.ents if annotate_ents is set
if self.annotate_ents:
spans = []
if not self.overwrite:
spans = list(doc.ents)
spans = self.ents_filter(spans, matches)
try:
doc.ents = sorted(spans)
except ValueError:
raise ValueError(Errors.E854)
@property
def labels(self) -> Tuple[str, ...]:
"""All labels present in the match patterns.
RETURNS (set): The string labels.
DOCS: https://spacy.io/api/spanruler#labels
"""
return tuple(sorted(set([cast(str, p["label"]) for p in self._patterns])))
@property
def ids(self) -> Tuple[str, ...]:
"""All IDs present in the match patterns.
RETURNS (set): The string IDs.
DOCS: https://spacy.io/api/spanruler#ids
"""
return tuple(
sorted(set([cast(str, p.get("id")) for p in self._patterns]) - set([None]))
)
def initialize(
self,
get_examples: Callable[[], Iterable[Example]],
*,
nlp: Optional[Language] = None,
patterns: Optional[Sequence[PatternType]] = None,
):
"""Initialize the pipe for training.
get_examples (Callable[[], Iterable[Example]]): Function that
returns a representative sample of gold-standard Example objects.
nlp (Language): The current nlp object the component is part of.
patterns (Optional[Iterable[PatternType]]): The list of patterns.
DOCS: https://spacy.io/api/spanruler#initialize
"""
self.clear()
if patterns:
self.add_patterns(patterns) # type: ignore[arg-type]
@property
def patterns(self) -> List[PatternType]:
"""Get all patterns that were added to the span ruler.
RETURNS (list): The original patterns, one dictionary per pattern.
DOCS: https://spacy.io/api/spanruler#patterns
"""
return self._patterns
def add_patterns(self, patterns: List[PatternType]) -> None:
"""Add patterns to the span ruler. A pattern can either be a token
pattern (list of dicts) or a phrase pattern (string). For example:
{'label': 'ORG', 'pattern': 'Apple'}
{'label': 'ORG', 'pattern': 'Apple', 'id': 'apple'}
{'label': 'GPE', 'pattern': [{'lower': 'san'}, {'lower': 'francisco'}]}
patterns (list): The patterns to add.
DOCS: https://spacy.io/api/spanruler#add_patterns
"""
# disable the nlp components after this one in case they haven't been
# initialized / deserialized yet
try:
current_index = -1
for i, (name, pipe) in enumerate(self.nlp.pipeline):
if self == pipe:
current_index = i
break
subsequent_pipes = [pipe for pipe in self.nlp.pipe_names[current_index:]]
except ValueError:
subsequent_pipes = []
with self.nlp.select_pipes(disable=subsequent_pipes):
phrase_pattern_labels = []
phrase_pattern_texts = []
for entry in patterns:
p_label = cast(str, entry["label"])
p_id = cast(str, entry.get("id", ""))
label = repr((p_label, p_id))
self._match_label_id_map[self.nlp.vocab.strings.as_int(label)] = {
"label": p_label,
"id": p_id,
}
if isinstance(entry["pattern"], str):
phrase_pattern_labels.append(label)
phrase_pattern_texts.append(entry["pattern"])
elif isinstance(entry["pattern"], list):
self.matcher.add(label, [entry["pattern"]])
else:
raise ValueError(Errors.E097.format(pattern=entry["pattern"]))
self._patterns.append(entry)
for label, pattern in zip(
phrase_pattern_labels,
self.nlp.pipe(phrase_pattern_texts),
):
self.phrase_matcher.add(label, [pattern])
def clear(self) -> None:
"""Reset all patterns.
RETURNS: None
DOCS: https://spacy.io/api/spanruler#clear
"""
self._patterns: List[PatternType] = []
self.matcher: Matcher = Matcher(self.nlp.vocab, validate=self.validate)
self.phrase_matcher: PhraseMatcher = PhraseMatcher(
self.nlp.vocab,
attr=self.phrase_matcher_attr,
validate=self.validate,
)
def remove(self, label: str) -> None:
"""Remove a pattern by its label.
label (str): Label of the pattern to be removed.
RETURNS: None
DOCS: https://spacy.io/api/spanruler#remove
"""
if label not in self:
raise ValueError(
Errors.E1024.format(attr_type="label", label=label, component=self.name)
)
self._patterns = [p for p in self._patterns if p["label"] != label]
for m_label in self._match_label_id_map:
if self._match_label_id_map[m_label]["label"] == label:
m_label_str = self.nlp.vocab.strings.as_string(m_label)
if m_label_str in self.phrase_matcher:
self.phrase_matcher.remove(m_label_str)
if m_label_str in self.matcher:
self.matcher.remove(m_label_str)
def remove_by_id(self, pattern_id: str) -> None:
"""Remove a pattern by its pattern ID.
pattern_id (str): ID of the pattern to be removed.
RETURNS: None
DOCS: https://spacy.io/api/spanruler#remove_by_id
"""
orig_len = len(self)
self._patterns = [p for p in self._patterns if p.get("id") != pattern_id]
if orig_len == len(self):
raise ValueError(
Errors.E1024.format(
attr_type="ID", label=pattern_id, component=self.name
)
)
for m_label in self._match_label_id_map:
if self._match_label_id_map[m_label]["id"] == pattern_id:
m_label_str = self.nlp.vocab.strings.as_string(m_label)
if m_label_str in self.phrase_matcher:
self.phrase_matcher.remove(m_label_str)
if m_label_str in self.matcher:
self.matcher.remove(m_label_str)
def _require_patterns(self) -> None:
"""Raise a warning if this component has no patterns defined."""
if len(self) == 0:
warnings.warn(Warnings.W036.format(name=self.name))
def from_bytes(
self, bytes_data: bytes, *, exclude: Iterable[str] = SimpleFrozenList()
) -> "SpanRuler":
"""Load the span ruler from a bytestring.
bytes_data (bytes): The bytestring to load.
RETURNS (SpanRuler): The loaded span ruler.
DOCS: https://spacy.io/api/spanruler#from_bytes
"""
self.clear()
deserializers = {
"patterns": lambda b: self.add_patterns(srsly.json_loads(b)),
}
util.from_bytes(bytes_data, deserializers, exclude)
return self
def to_bytes(self, *, exclude: Iterable[str] = SimpleFrozenList()) -> bytes:
"""Serialize the span ruler to a bytestring.
RETURNS (bytes): The serialized patterns.
DOCS: https://spacy.io/api/spanruler#to_bytes
"""
serializers = {
"patterns": lambda: srsly.json_dumps(self.patterns),
}
return util.to_bytes(serializers, exclude)
def from_disk(
self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
) -> "SpanRuler":
"""Load the span ruler from a directory.
path (Union[str, Path]): A path to a directory.
RETURNS (SpanRuler): The loaded span ruler.
DOCS: https://spacy.io/api/spanruler#from_disk
"""
self.clear()
path = ensure_path(path)
deserializers = {
"patterns": lambda p: self.add_patterns(srsly.read_jsonl(p)),
}
util.from_disk(path, deserializers, {})
return self
def to_disk(
self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
) -> None:
"""Save the span ruler patterns to a directory.
path (Union[str, Path]): A path to a directory.
DOCS: https://spacy.io/api/spanruler#to_disk
"""
path = ensure_path(path)
serializers = {
"patterns": lambda p: srsly.write_jsonl(p, self.patterns),
}
util.to_disk(path, serializers, {})

26
spacy/schemas.py
View File

@ -485,3 +485,29 @@ class RecommendationSchema(BaseModel):
word_vectors: Optional[str] = None
transformer: Optional[RecommendationTrf] = None
has_letters: bool = True
class DocJSONSchema(BaseModel):
"""
JSON/dict format for JSON representation of Doc objects.
"""
cats: Optional[Dict[StrictStr, StrictFloat]] = Field(
None, title="Categories with corresponding probabilities"
)
ents: Optional[List[Dict[StrictStr, Union[StrictInt, StrictStr]]]] = Field(
None, title="Information on entities"
)
sents: Optional[List[Dict[StrictStr, StrictInt]]] = Field(
None, title="Indices of sentences' start and end indices"
)
text: StrictStr = Field(..., title="Document text")
spans: Dict[StrictStr, List[Dict[StrictStr, Union[StrictStr, StrictInt]]]] = Field(
None, title="Span information - end/start indices, label, KB ID"
)
tokens: List[Dict[StrictStr, Union[StrictStr, StrictInt]]] = Field(
..., title="Token information - ID, start, annotations"
)
_: Optional[Dict[StrictStr, Any]] = Field(
None, title="Any custom data stored in the document's _ attribute"
)

191
spacy/tests/doc/test_json_doc_conversion.py Normal file
View File

@ -0,0 +1,191 @@
import pytest
import spacy
from spacy import schemas
from spacy.tokens import Doc, Span
@pytest.fixture()
def doc(en_vocab):
words = ["c", "d", "e"]
pos = ["VERB", "NOUN", "NOUN"]
tags = ["VBP", "NN", "NN"]
heads = [0, 0, 1]
deps = ["ROOT", "dobj", "dobj"]
ents = ["O", "B-ORG", "O"]
morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
return Doc(
en_vocab,
words=words,
pos=pos,
tags=tags,
heads=heads,
deps=deps,
ents=ents,
morphs=morphs,
)
@pytest.fixture()
def doc_without_deps(en_vocab):
words = ["c", "d", "e"]
pos = ["VERB", "NOUN", "NOUN"]
tags = ["VBP", "NN", "NN"]
ents = ["O", "B-ORG", "O"]
morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
return Doc(
en_vocab,
words=words,
pos=pos,
tags=tags,
ents=ents,
morphs=morphs,
sent_starts=[True, False, True],
)
def test_doc_to_json(doc):
json_doc = doc.to_json()
assert json_doc["text"] == "c d e "
assert len(json_doc["tokens"]) == 3
assert json_doc["tokens"][0]["pos"] == "VERB"
assert json_doc["tokens"][0]["tag"] == "VBP"
assert json_doc["tokens"][0]["dep"] == "ROOT"
assert len(json_doc["ents"]) == 1
assert json_doc["ents"][0]["start"] == 2 # character offset!
assert json_doc["ents"][0]["end"] == 3 # character offset!
assert json_doc["ents"][0]["label"] == "ORG"
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_doc_to_json_underscore(doc):
Doc.set_extension("json_test1", default=False)
Doc.set_extension("json_test2", default=False)
doc._.json_test1 = "hello world"
doc._.json_test2 = [1, 2, 3]
json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
assert "_" in json_doc
assert json_doc["_"]["json_test1"] == "hello world"
assert json_doc["_"]["json_test2"] == [1, 2, 3]
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_doc_to_json_underscore_error_attr(doc):
"""Test that Doc.to_json() raises an error if a custom attribute doesn't
exist in the ._ space."""
with pytest.raises(ValueError):
doc.to_json(underscore=["json_test3"])
def test_doc_to_json_underscore_error_serialize(doc):
"""Test that Doc.to_json() raises an error if a custom attribute value
isn't JSON-serializable."""
Doc.set_extension("json_test4", method=lambda doc: doc.text)
with pytest.raises(ValueError):
doc.to_json(underscore=["json_test4"])
def test_doc_to_json_span(doc):
"""Test that Doc.to_json() includes spans"""
doc.spans["test"] = [Span(doc, 0, 2, "test"), Span(doc, 0, 1, "test")]
json_doc = doc.to_json()
assert "spans" in json_doc
assert len(json_doc["spans"]) == 1
assert len(json_doc["spans"]["test"]) == 2
assert json_doc["spans"]["test"][0]["start"] == 0
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_json_to_doc(doc):
new_doc = Doc(doc.vocab).from_json(doc.to_json(), validate=True)
new_tokens = [token for token in new_doc]
assert new_doc.text == doc.text == "c d e "
assert len(new_tokens) == len([token for token in doc]) == 3
assert new_tokens[0].pos == doc[0].pos
assert new_tokens[0].tag == doc[0].tag
assert new_tokens[0].dep == doc[0].dep
assert new_tokens[0].head.idx == doc[0].head.idx
assert new_tokens[0].lemma == doc[0].lemma
assert len(new_doc.ents) == 1
assert new_doc.ents[0].start == 1
assert new_doc.ents[0].end == 2
assert new_doc.ents[0].label_ == "ORG"
def test_json_to_doc_underscore(doc):
if not Doc.has_extension("json_test1"):
Doc.set_extension("json_test1", default=False)
if not Doc.has_extension("json_test2"):
Doc.set_extension("json_test2", default=False)
doc._.json_test1 = "hello world"
doc._.json_test2 = [1, 2, 3]
json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
assert all([new_doc.has_extension(f"json_test{i}") for i in range(1, 3)])
assert new_doc._.json_test1 == "hello world"
assert new_doc._.json_test2 == [1, 2, 3]
def test_json_to_doc_spans(doc):
"""Test that Doc.from_json() includes correct.spans."""
doc.spans["test"] = [
Span(doc, 0, 2, label="test"),
Span(doc, 0, 1, label="test", kb_id=7),
]
json_doc = doc.to_json()
new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
assert len(new_doc.spans) == 1
assert len(new_doc.spans["test"]) == 2
for i in range(2):
assert new_doc.spans["test"][i].start == doc.spans["test"][i].start
assert new_doc.spans["test"][i].end == doc.spans["test"][i].end
assert new_doc.spans["test"][i].label == doc.spans["test"][i].label
assert new_doc.spans["test"][i].kb_id == doc.spans["test"][i].kb_id
def test_json_to_doc_sents(doc, doc_without_deps):
"""Test that Doc.from_json() includes correct.sents."""
for test_doc in (doc, doc_without_deps):
json_doc = test_doc.to_json()
new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
assert [sent.text for sent in test_doc.sents] == [
sent.text for sent in new_doc.sents
]
assert [token.is_sent_start for token in test_doc] == [
token.is_sent_start for token in new_doc
]
def test_json_to_doc_cats(doc):
"""Test that Doc.from_json() includes correct .cats."""
cats = {"A": 0.3, "B": 0.7}
doc.cats = cats
json_doc = doc.to_json()
new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
assert new_doc.cats == cats
def test_json_to_doc_spaces():
"""Test that Doc.from_json() preserves spaces correctly."""
doc = spacy.blank("en")("This is just brilliant.")
json_doc = doc.to_json()
new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
assert doc.text == new_doc.text
def test_json_to_doc_attribute_consistency(doc):
"""Test that Doc.from_json() raises an exception if tokens don't all have the same set of properties."""
doc_json = doc.to_json()
doc_json["tokens"][1].pop("morph")
with pytest.raises(ValueError):
Doc(doc.vocab).from_json(doc_json)
def test_json_to_doc_validation_error(doc):
"""Test that Doc.from_json() raises an exception when validating invalid input."""
doc_json = doc.to_json()
doc_json.pop("tokens")
with pytest.raises(ValueError):
Doc(doc.vocab).from_json(doc_json, validate=True)

2
spacy/tests/doc/test_pickle_doc.py
View File

@ -5,11 +5,9 @@ from spacy.compat import pickle
def test_pickle_single_doc():
nlp = Language()
doc = nlp("pickle roundtrip")
doc._context = 3
data = pickle.dumps(doc, 1)
doc2 = pickle.loads(data)
assert doc2.text == "pickle roundtrip"
assert doc2._context == 3
def test_list_of_docs_pickles_efficiently():

12
spacy/tests/doc/test_span.py
View File

@ -428,10 +428,19 @@ def test_span_string_label_kb_id(doc):
assert span.kb_id == doc.vocab.strings["Q342"]
def test_span_string_label_id(doc):
span = Span(doc, 0, 1, label="hello", span_id="Q342")
assert span.label_ == "hello"
assert span.label == doc.vocab.strings["hello"]
assert span.id_ == "Q342"
assert span.id == doc.vocab.strings["Q342"]
def test_span_attrs_writable(doc):
span = Span(doc, 0, 1)
span.label_ = "label"
span.kb_id_ = "kb_id"
span.id_ = "id"
def test_span_ents_property(doc):
@ -619,6 +628,9 @@ def test_span_comparison(doc):
assert Span(doc, 0, 4, "LABEL", kb_id="KB_ID") <= Span(doc, 1, 3)
assert Span(doc, 1, 3) > Span(doc, 0, 4, "LABEL", kb_id="KB_ID")
assert Span(doc, 1, 3) >= Span(doc, 0, 4, "LABEL", kb_id="KB_ID")
# Different id
assert Span(doc, 1, 3, span_id="AAA") < Span(doc, 1, 3, span_id="BBB")
# fmt: on

72
spacy/tests/doc/test_to_json.py
View File

@ -1,72 +0,0 @@
import pytest
from spacy.tokens import Doc, Span
@pytest.fixture()
def doc(en_vocab):
words = ["c", "d", "e"]
pos = ["VERB", "NOUN", "NOUN"]
tags = ["VBP", "NN", "NN"]
heads = [0, 0, 0]
deps = ["ROOT", "dobj", "dobj"]
ents = ["O", "B-ORG", "O"]
morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
return Doc(
en_vocab,
words=words,
pos=pos,
tags=tags,
heads=heads,
deps=deps,
ents=ents,
morphs=morphs,
)
def test_doc_to_json(doc):
json_doc = doc.to_json()
assert json_doc["text"] == "c d e "
assert len(json_doc["tokens"]) == 3
assert json_doc["tokens"][0]["pos"] == "VERB"
assert json_doc["tokens"][0]["tag"] == "VBP"
assert json_doc["tokens"][0]["dep"] == "ROOT"
assert len(json_doc["ents"]) == 1
assert json_doc["ents"][0]["start"] == 2 # character offset!
assert json_doc["ents"][0]["end"] == 3 # character offset!
assert json_doc["ents"][0]["label"] == "ORG"
def test_doc_to_json_underscore(doc):
Doc.set_extension("json_test1", default=False)
Doc.set_extension("json_test2", default=False)
doc._.json_test1 = "hello world"
doc._.json_test2 = [1, 2, 3]
json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
assert "_" in json_doc
assert json_doc["_"]["json_test1"] == "hello world"
assert json_doc["_"]["json_test2"] == [1, 2, 3]
def test_doc_to_json_underscore_error_attr(doc):
"""Test that Doc.to_json() raises an error if a custom attribute doesn't
exist in the ._ space."""
with pytest.raises(ValueError):
doc.to_json(underscore=["json_test3"])
def test_doc_to_json_underscore_error_serialize(doc):
"""Test that Doc.to_json() raises an error if a custom attribute value
isn't JSON-serializable."""
Doc.set_extension("json_test4", method=lambda doc: doc.text)
with pytest.raises(ValueError):
doc.to_json(underscore=["json_test4"])
def test_doc_to_json_span(doc):
"""Test that Doc.to_json() includes spans"""
doc.spans["test"] = [Span(doc, 0, 2, "test"), Span(doc, 0, 1, "test")]
json_doc = doc.to_json()
assert "spans" in json_doc
assert len(json_doc["spans"]) == 1
assert len(json_doc["spans"]["test"]) == 2
assert json_doc["spans"]["test"][0]["start"] == 0

297
spacy/tests/pipeline/test_entity_ruler.py
View File

@ -5,12 +5,15 @@ from spacy.tokens import Doc, Span
from spacy.language import Language
from spacy.lang.en import English
from spacy.pipeline import EntityRuler, EntityRecognizer, merge_entities
from spacy.pipeline import SpanRuler
from spacy.pipeline.ner import DEFAULT_NER_MODEL
from spacy.errors import MatchPatternError
from spacy.tests.util import make_tempdir
from thinc.api import NumpyOps, get_current_ops
ENTITY_RULERS = ["entity_ruler", "future_entity_ruler"]
@pytest.fixture
def nlp():
@ -37,12 +40,14 @@ def add_ent_component(doc):
@pytest.mark.issue(3345)
def test_issue3345():
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_issue3345(entity_ruler_factory):
"""Test case where preset entity crosses sentence boundary."""
nlp = English()
doc = Doc(nlp.vocab, words=["I", "live", "in", "New", "York"])
doc[4].is_sent_start = True
ruler = EntityRuler(nlp, patterns=[{"label": "GPE", "pattern": "New York"}])
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns([{"label": "GPE", "pattern": "New York"}])
cfg = {"model": DEFAULT_NER_MODEL}
model = registry.resolve(cfg, validate=True)["model"]
ner = EntityRecognizer(doc.vocab, model)
@ -60,13 +65,18 @@ def test_issue3345():
@pytest.mark.issue(4849)
def test_issue4849():
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_issue4849(entity_ruler_factory):
nlp = English()
patterns = [
{"label": "PERSON", "pattern": "joe biden", "id": "joe-biden"},
{"label": "PERSON", "pattern": "bernie sanders", "id": "bernie-sanders"},
]
ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
ruler = nlp.add_pipe(
entity_ruler_factory,
name="entity_ruler",
config={"phrase_matcher_attr": "LOWER"},
)
ruler.add_patterns(patterns)
text = """
The left is starting to take aim at Democratic front-runner Joe Biden.
@ -86,10 +96,11 @@ def test_issue4849():
@pytest.mark.issue(5918)
def test_issue5918():
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_issue5918(entity_ruler_factory):
# Test edge case when merging entities.
nlp = English()
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "ORG", "pattern": "Digicon Inc"},
{"label": "ORG", "pattern": "Rotan Mosle Inc's"},
@ -114,9 +125,10 @@ def test_issue5918():
@pytest.mark.issue(8168)
def test_issue8168():
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_issue8168(entity_ruler_factory):
nlp = English()
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "ORG", "pattern": "Apple"},
{
@ -131,14 +143,17 @@ def test_issue8168():
},
]
ruler.add_patterns(patterns)
assert ruler._ent_ids == {8043148519967183733: ("GPE", "san-francisco")}
doc = nlp("San Francisco San Fran")
assert all(t.ent_id_ == "san-francisco" for t in doc)
@pytest.mark.issue(8216)
def test_entity_ruler_fix8216(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_fix8216(nlp, patterns, entity_ruler_factory):
"""Test that patterns don't get added excessively."""
ruler = nlp.add_pipe("entity_ruler", config={"validate": True})
ruler = nlp.add_pipe(
entity_ruler_factory, name="entity_ruler", config={"validate": True}
)
ruler.add_patterns(patterns)
pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
assert pattern_count > 0
@ -147,13 +162,16 @@ def test_entity_ruler_fix8216(nlp, patterns):
assert after_count == pattern_count
def test_entity_ruler_init(nlp, patterns):
ruler = EntityRuler(nlp, patterns=patterns)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_init(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
assert len(ruler) == len(patterns)
assert len(ruler.labels) == 4
assert "HELLO" in ruler
assert "BYE" in ruler
ruler = nlp.add_pipe("entity_ruler")
nlp.remove_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
doc = nlp("hello world bye bye")
assert len(doc.ents) == 2
@ -161,20 +179,23 @@ def test_entity_ruler_init(nlp, patterns):
assert doc.ents[1].label_ == "BYE"
def test_entity_ruler_no_patterns_warns(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_no_patterns_warns(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
assert len(ruler) == 0
assert len(ruler.labels) == 0
nlp.add_pipe("entity_ruler")
nlp.remove_pipe("entity_ruler")
nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
assert nlp.pipe_names == ["entity_ruler"]
with pytest.warns(UserWarning):
doc = nlp("hello world bye bye")
assert len(doc.ents) == 0
def test_entity_ruler_init_patterns(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_init_patterns(nlp, patterns, entity_ruler_factory):
# initialize with patterns
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
assert len(ruler.labels) == 0
ruler.initialize(lambda: [], patterns=patterns)
assert len(ruler.labels) == 4
@ -186,7 +207,7 @@ def test_entity_ruler_init_patterns(nlp, patterns):
nlp.config["initialize"]["components"]["entity_ruler"] = {
"patterns": {"@misc": "entity_ruler_patterns"}
}
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
assert len(ruler.labels) == 0
nlp.initialize()
assert len(ruler.labels) == 4
@ -195,18 +216,20 @@ def test_entity_ruler_init_patterns(nlp, patterns):
assert doc.ents[1].label_ == "BYE"
def test_entity_ruler_init_clear(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_init_clear(nlp, patterns, entity_ruler_factory):
"""Test that initialization clears patterns."""
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
assert len(ruler.labels) == 4
ruler.initialize(lambda: [])
assert len(ruler.labels) == 0
def test_entity_ruler_clear(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_clear(nlp, patterns, entity_ruler_factory):
"""Test that initialization clears patterns."""
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
assert len(ruler.labels) == 4
doc = nlp("hello world")
@ -218,8 +241,9 @@ def test_entity_ruler_clear(nlp, patterns):
assert len(doc.ents) == 0
def test_entity_ruler_existing(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler")
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_existing(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
nlp.add_pipe("add_ent", before="entity_ruler")
doc = nlp("OH HELLO WORLD bye bye")
@ -228,8 +252,11 @@ def test_entity_ruler_existing(nlp, patterns):
assert doc.ents[1].label_ == "BYE"
def test_entity_ruler_existing_overwrite(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_existing_overwrite(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(
entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
)
ruler.add_patterns(patterns)
nlp.add_pipe("add_ent", before="entity_ruler")
doc = nlp("OH HELLO WORLD bye bye")
@ -239,8 +266,11 @@ def test_entity_ruler_existing_overwrite(nlp, patterns):
assert doc.ents[1].label_ == "BYE"
def test_entity_ruler_existing_complex(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_existing_complex(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(
entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
)
ruler.add_patterns(patterns)
nlp.add_pipe("add_ent", before="entity_ruler")
doc = nlp("foo foo bye bye")
@ -251,8 +281,11 @@ def test_entity_ruler_existing_complex(nlp, patterns):
assert len(doc.ents[1]) == 2
def test_entity_ruler_entity_id(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_entity_id(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(
entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
)
ruler.add_patterns(patterns)
doc = nlp("Apple is a technology company")
assert len(doc.ents) == 1
@ -260,18 +293,21 @@ def test_entity_ruler_entity_id(nlp, patterns):
assert doc.ents[0].ent_id_ == "a1"
def test_entity_ruler_cfg_ent_id_sep(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_cfg_ent_id_sep(nlp, patterns, entity_ruler_factory):
config = {"overwrite_ents": True, "ent_id_sep": "**"}
ruler = nlp.add_pipe("entity_ruler", config=config)
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler", config=config)
ruler.add_patterns(patterns)
assert "TECH_ORG**a1" in ruler.phrase_patterns
doc = nlp("Apple is a technology company")
if isinstance(ruler, EntityRuler):
assert "TECH_ORG**a1" in ruler.phrase_patterns
assert len(doc.ents) == 1
assert doc.ents[0].label_ == "TECH_ORG"
assert doc.ents[0].ent_id_ == "a1"
def test_entity_ruler_serialize_bytes(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_serialize_bytes(nlp, patterns, entity_ruler_factory):
ruler = EntityRuler(nlp, patterns=patterns)
assert len(ruler) == len(patterns)
assert len(ruler.labels) == 4
@ -288,7 +324,10 @@ def test_entity_ruler_serialize_bytes(nlp, patterns):
assert sorted(new_ruler.labels) == sorted(ruler.labels)
def test_entity_ruler_serialize_phrase_matcher_attr_bytes(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_serialize_phrase_matcher_attr_bytes(
nlp, patterns, entity_ruler_factory
):
ruler = EntityRuler(nlp, phrase_matcher_attr="LOWER", patterns=patterns)
assert len(ruler) == len(patterns)
assert len(ruler.labels) == 4
@ -303,8 +342,9 @@ def test_entity_ruler_serialize_phrase_matcher_attr_bytes(nlp, patterns):
assert new_ruler.phrase_matcher_attr == "LOWER"
def test_entity_ruler_validate(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_validate(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
validated_ruler = EntityRuler(nlp, validate=True)
valid_pattern = {"label": "HELLO", "pattern": [{"LOWER": "HELLO"}]}
@ -322,32 +362,35 @@ def test_entity_ruler_validate(nlp):
validated_ruler.add_patterns([invalid_pattern])
def test_entity_ruler_properties(nlp, patterns):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_properties(nlp, patterns, entity_ruler_factory):
ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
assert sorted(ruler.labels) == sorted(["HELLO", "BYE", "COMPLEX", "TECH_ORG"])
assert sorted(ruler.ent_ids) == ["a1", "a2"]
def test_entity_ruler_overlapping_spans(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_overlapping_spans(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "FOOBAR", "pattern": "foo bar"},
{"label": "BARBAZ", "pattern": "bar baz"},
]
ruler.add_patterns(patterns)
doc = ruler(nlp.make_doc("foo bar baz"))
doc = nlp("foo bar baz")
assert len(doc.ents) == 1
assert doc.ents[0].label_ == "FOOBAR"
@pytest.mark.parametrize("n_process", [1, 2])
def test_entity_ruler_multiprocessing(nlp, n_process):
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_multiprocessing(nlp, n_process, entity_ruler_factory):
if isinstance(get_current_ops, NumpyOps) or n_process < 2:
texts = ["I enjoy eating Pizza Hut pizza."]
patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}]
ruler = nlp.add_pipe("entity_ruler")
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
for doc in nlp.pipe(texts, n_process=2):
@ -355,8 +398,9 @@ def test_entity_ruler_multiprocessing(nlp, n_process):
assert ent.ent_id_ == "1234"
def test_entity_ruler_serialize_jsonl(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler")
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_serialize_jsonl(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
with make_tempdir() as d:
ruler.to_disk(d / "test_ruler.jsonl")
@ -365,8 +409,9 @@ def test_entity_ruler_serialize_jsonl(nlp, patterns):
ruler.from_disk(d / "non_existing.jsonl") # read from a bad jsonl file
def test_entity_ruler_serialize_dir(nlp, patterns):
ruler = nlp.add_pipe("entity_ruler")
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_serialize_dir(nlp, patterns, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
ruler.add_patterns(patterns)
with make_tempdir() as d:
ruler.to_disk(d / "test_ruler")
@ -375,52 +420,65 @@ def test_entity_ruler_serialize_dir(nlp, patterns):
ruler.from_disk(d / "non_existing_dir") # read from a bad directory
def test_entity_ruler_remove_basic(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_basic(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
{"label": "ORG", "pattern": "ACM"},
]
ruler.add_patterns(patterns)
doc = ruler(nlp.make_doc("Duygu went to school"))
doc = nlp("Dina went to school")
assert len(ruler.patterns) == 3
assert len(doc.ents) == 1
if isinstance(ruler, EntityRuler):
assert "PERSON||dina" in ruler.phrase_matcher
assert doc.ents[0].label_ == "PERSON"
assert doc.ents[0].text == "Duygu"
assert "PERSON||duygu" in ruler.phrase_matcher
ruler.remove("duygu")
doc = ruler(nlp.make_doc("Duygu went to school"))
assert doc.ents[0].text == "Dina"
if isinstance(ruler, EntityRuler):
ruler.remove("dina")
else:
ruler.remove_by_id("dina")
doc = nlp("Dina went to school")
assert len(doc.ents) == 0
assert "PERSON||duygu" not in ruler.phrase_matcher
if isinstance(ruler, EntityRuler):
assert "PERSON||dina" not in ruler.phrase_matcher
assert len(ruler.patterns) == 2
def test_entity_ruler_remove_same_id_multiple_patterns(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_same_id_multiple_patterns(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "ORG", "pattern": "DuyguCorp", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "DinaCorp", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
]
ruler.add_patterns(patterns)
doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
doc = nlp("Dina founded DinaCorp and ACME.")
assert len(ruler.patterns) == 3
assert "PERSON||duygu" in ruler.phrase_matcher
assert "ORG||duygu" in ruler.phrase_matcher
if isinstance(ruler, EntityRuler):
assert "PERSON||dina" in ruler.phrase_matcher
assert "ORG||dina" in ruler.phrase_matcher
assert len(doc.ents) == 3
ruler.remove("duygu")
doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
if isinstance(ruler, EntityRuler):
ruler.remove("dina")
else:
ruler.remove_by_id("dina")
doc = nlp("Dina founded DinaCorp and ACME.")
assert len(ruler.patterns) == 1
assert "PERSON||duygu" not in ruler.phrase_matcher
assert "ORG||duygu" not in ruler.phrase_matcher
if isinstance(ruler, EntityRuler):
assert "PERSON||dina" not in ruler.phrase_matcher
assert "ORG||dina" not in ruler.phrase_matcher
assert len(doc.ents) == 1
def test_entity_ruler_remove_nonexisting_pattern(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_nonexisting_pattern(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
{"label": "ORG", "pattern": "ACM"},
]
@ -428,82 +486,109 @@ def test_entity_ruler_remove_nonexisting_pattern(nlp):
assert len(ruler.patterns) == 3
with pytest.raises(ValueError):
ruler.remove("nepattern")
assert len(ruler.patterns) == 3
if isinstance(ruler, SpanRuler):
with pytest.raises(ValueError):
ruler.remove_by_id("nepattern")
def test_entity_ruler_remove_several_patterns(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_several_patterns(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
{"label": "ORG", "pattern": "ACM"},
]
ruler.add_patterns(patterns)
doc = ruler(nlp.make_doc("Duygu founded her company ACME."))
doc = nlp("Dina founded her company ACME.")
assert len(ruler.patterns) == 3
assert len(doc.ents) == 2
assert doc.ents[0].label_ == "PERSON"
assert doc.ents[0].text == "Duygu"
assert doc.ents[0].text == "Dina"
assert doc.ents[1].label_ == "ORG"
assert doc.ents[1].text == "ACME"
ruler.remove("duygu")
doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
if isinstance(ruler, EntityRuler):
ruler.remove("dina")
else:
ruler.remove_by_id("dina")
doc = nlp("Dina founded her company ACME")
assert len(ruler.patterns) == 2
assert len(doc.ents) == 1
assert doc.ents[0].label_ == "ORG"
assert doc.ents[0].text == "ACME"
ruler.remove("acme")
doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
if isinstance(ruler, EntityRuler):
ruler.remove("acme")
else:
ruler.remove_by_id("acme")
doc = nlp("Dina founded her company ACME")
assert len(ruler.patterns) == 1
assert len(doc.ents) == 0
def test_entity_ruler_remove_patterns_in_a_row(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_patterns_in_a_row(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
{"label": "DATE", "pattern": "her birthday", "id": "bday"},
{"label": "ORG", "pattern": "ACM"},
]
ruler.add_patterns(patterns)
doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
doc = nlp("Dina founded her company ACME on her birthday")
assert len(doc.ents) == 3
assert doc.ents[0].label_ == "PERSON"
assert doc.ents[0].text == "Duygu"
assert doc.ents[0].text == "Dina"
assert doc.ents[1].label_ == "ORG"
assert doc.ents[1].text == "ACME"
assert doc.ents[2].label_ == "DATE"
assert doc.ents[2].text == "her birthday"
ruler.remove("duygu")
ruler.remove("acme")
ruler.remove("bday")
doc = ruler(nlp.make_doc("Duygu went to school"))
if isinstance(ruler, EntityRuler):
ruler.remove("dina")
ruler.remove("acme")
ruler.remove("bday")
else:
ruler.remove_by_id("dina")
ruler.remove_by_id("acme")
ruler.remove_by_id("bday")
doc = nlp("Dina went to school")
assert len(doc.ents) == 0
def test_entity_ruler_remove_all_patterns(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_all_patterns(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [
{"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
{"label": "PERSON", "pattern": "Dina", "id": "dina"},
{"label": "ORG", "pattern": "ACME", "id": "acme"},
{"label": "DATE", "pattern": "her birthday", "id": "bday"},
]
ruler.add_patterns(patterns)
assert len(ruler.patterns) == 3
ruler.remove("duygu")
if isinstance(ruler, EntityRuler):
ruler.remove("dina")
else:
ruler.remove_by_id("dina")
assert len(ruler.patterns) == 2
ruler.remove("acme")
if isinstance(ruler, EntityRuler):
ruler.remove("acme")
else:
ruler.remove_by_id("acme")
assert len(ruler.patterns) == 1
ruler.remove("bday")
if isinstance(ruler, EntityRuler):
ruler.remove("bday")
else:
ruler.remove_by_id("bday")
assert len(ruler.patterns) == 0
with pytest.warns(UserWarning):
doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
doc = nlp("Dina founded her company ACME on her birthday")
assert len(doc.ents) == 0
def test_entity_ruler_remove_and_add(nlp):
ruler = EntityRuler(nlp)
@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
def test_entity_ruler_remove_and_add(nlp, entity_ruler_factory):
ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
patterns = [{"label": "DATE", "pattern": "last time"}]
ruler.add_patterns(patterns)
doc = ruler(
@ -524,7 +609,10 @@ def test_entity_ruler_remove_and_add(nlp):
assert doc.ents[0].text == "last time"
assert doc.ents[1].label_ == "DATE"
assert doc.ents[1].text == "this time"
ruler.remove("ttime")
if isinstance(ruler, EntityRuler):
ruler.remove("ttime")
else:
ruler.remove_by_id("ttime")
doc = ruler(
nlp.make_doc("I saw him last time we met, this time he brought some flowers")
)
@ -547,7 +635,10 @@ def test_entity_ruler_remove_and_add(nlp):
)
assert len(ruler.patterns) == 3
assert len(doc.ents) == 3
ruler.remove("ttime")
if isinstance(ruler, EntityRuler):
ruler.remove("ttime")
else:
ruler.remove_by_id("ttime")
doc = ruler(
nlp.make_doc(
"I saw him last time we met, this time he brought some flowers, another time some chocolate."

465
spacy/tests/pipeline/test_span_ruler.py Normal file
View File

@ -0,0 +1,465 @@
import pytest
import spacy
from spacy import registry
from spacy.errors import MatchPatternError
from spacy.tokens import Span
from spacy.training import Example
from spacy.tests.util import make_tempdir
from thinc.api import NumpyOps, get_current_ops
@pytest.fixture
@registry.misc("span_ruler_patterns")
def patterns():
return [
{"label": "HELLO", "pattern": "hello world", "id": "hello1"},
{"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
{"label": "HELLO", "pattern": [{"ORTH": "HELLO"}], "id": "hello2"},
{"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
{"label": "TECH_ORG", "pattern": "Apple"},
{"label": "TECH_ORG", "pattern": "Microsoft"},
]
@pytest.fixture
def overlapping_patterns():
return [
{"label": "FOOBAR", "pattern": "foo bar"},
{"label": "BARBAZ", "pattern": "bar baz"},
]
@pytest.fixture
def person_org_patterns():
return [
{"label": "PERSON", "pattern": "Dina"},
{"label": "ORG", "pattern": "ACME"},
{"label": "ORG", "pattern": "ACM"},
]
@pytest.fixture
def person_org_date_patterns(person_org_patterns):
return person_org_patterns + [{"label": "DATE", "pattern": "June 14th"}]
def test_span_ruler_add_empty(patterns):
"""Test that patterns don't get added excessively."""
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler", config={"validate": True})
ruler.add_patterns(patterns)
pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
assert pattern_count > 0
ruler.add_patterns([])
after_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
assert after_count == pattern_count
def test_span_ruler_init(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
assert len(ruler) == len(patterns)
assert len(ruler.labels) == 4
assert "HELLO" in ruler
assert "BYE" in ruler
doc = nlp("hello world bye bye")
assert len(doc.spans["ruler"]) == 2
assert doc.spans["ruler"][0].label_ == "HELLO"
assert doc.spans["ruler"][0].id_ == "hello1"
assert doc.spans["ruler"][1].label_ == "BYE"
assert doc.spans["ruler"][1].id_ == ""
def test_span_ruler_no_patterns_warns():
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
assert len(ruler) == 0
assert len(ruler.labels) == 0
assert nlp.pipe_names == ["span_ruler"]
with pytest.warns(UserWarning):
doc = nlp("hello world bye bye")
assert len(doc.spans["ruler"]) == 0
def test_span_ruler_init_patterns(patterns):
# initialize with patterns
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
assert len(ruler.labels) == 0
ruler.initialize(lambda: [], patterns=patterns)
assert len(ruler.labels) == 4
doc = nlp("hello world bye bye")
assert doc.spans["ruler"][0].label_ == "HELLO"
assert doc.spans["ruler"][1].label_ == "BYE"
nlp.remove_pipe("span_ruler")
# initialize with patterns from misc registry
nlp.config["initialize"]["components"]["span_ruler"] = {
"patterns": {"@misc": "span_ruler_patterns"}
}
ruler = nlp.add_pipe("span_ruler")
assert len(ruler.labels) == 0
nlp.initialize()
assert len(ruler.labels) == 4
doc = nlp("hello world bye bye")
assert doc.spans["ruler"][0].label_ == "HELLO"
assert doc.spans["ruler"][1].label_ == "BYE"
def test_span_ruler_init_clear(patterns):
"""Test that initialization clears patterns."""
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
assert len(ruler.labels) == 4
ruler.initialize(lambda: [])
assert len(ruler.labels) == 0
def test_span_ruler_clear(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
assert len(ruler.labels) == 4
doc = nlp("hello world")
assert len(doc.spans["ruler"]) == 1
ruler.clear()
assert len(ruler.labels) == 0
with pytest.warns(UserWarning):
doc = nlp("hello world")
assert len(doc.spans["ruler"]) == 0
def test_span_ruler_existing(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler", config={"overwrite": False})
ruler.add_patterns(patterns)
doc = nlp.make_doc("OH HELLO WORLD bye bye")
doc.spans["ruler"] = [doc[0:2]]
doc = nlp(doc)
assert len(doc.spans["ruler"]) == 3
assert doc.spans["ruler"][0] == doc[0:2]
assert doc.spans["ruler"][1].label_ == "HELLO"
assert doc.spans["ruler"][1].id_ == "hello2"
assert doc.spans["ruler"][2].label_ == "BYE"
assert doc.spans["ruler"][2].id_ == ""
def test_span_ruler_existing_overwrite(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler", config={"overwrite": True})
ruler.add_patterns(patterns)
doc = nlp.make_doc("OH HELLO WORLD bye bye")
doc.spans["ruler"] = [doc[0:2]]
doc = nlp(doc)
assert len(doc.spans["ruler"]) == 2
assert doc.spans["ruler"][0].label_ == "HELLO"
assert doc.spans["ruler"][0].text == "HELLO"
assert doc.spans["ruler"][1].label_ == "BYE"
def test_span_ruler_serialize_bytes(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
assert len(ruler) == len(patterns)
assert len(ruler.labels) == 4
ruler_bytes = ruler.to_bytes()
new_nlp = spacy.blank("xx")
new_ruler = new_nlp.add_pipe("span_ruler")
assert len(new_ruler) == 0
assert len(new_ruler.labels) == 0
new_ruler = new_ruler.from_bytes(ruler_bytes)
assert len(new_ruler) == len(patterns)
assert len(new_ruler.labels) == 4
assert len(new_ruler.patterns) == len(ruler.patterns)
for pattern in ruler.patterns:
assert pattern in new_ruler.patterns
assert sorted(new_ruler.labels) == sorted(ruler.labels)
def test_span_ruler_validate():
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
validated_ruler = nlp.add_pipe(
"span_ruler", name="validated_span_ruler", config={"validate": True}
)
valid_pattern = {"label": "HELLO", "pattern": [{"LOWER": "HELLO"}]}
invalid_pattern = {"label": "HELLO", "pattern": [{"ASDF": "HELLO"}]}
# invalid pattern raises error without validate
with pytest.raises(ValueError):
ruler.add_patterns([invalid_pattern])
# valid pattern is added without errors with validate
validated_ruler.add_patterns([valid_pattern])
# invalid pattern raises error with validate
with pytest.raises(MatchPatternError):
validated_ruler.add_patterns([invalid_pattern])
def test_span_ruler_properties(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler", config={"overwrite": True})
ruler.add_patterns(patterns)
assert sorted(ruler.labels) == sorted(set([p["label"] for p in patterns]))
def test_span_ruler_overlapping_spans(overlapping_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(overlapping_patterns)
doc = ruler(nlp.make_doc("foo bar baz"))
assert len(doc.spans["ruler"]) == 2
assert doc.spans["ruler"][0].label_ == "FOOBAR"
assert doc.spans["ruler"][1].label_ == "BARBAZ"
def test_span_ruler_scorer(overlapping_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(overlapping_patterns)
text = "foo bar baz"
pred_doc = ruler(nlp.make_doc(text))
assert len(pred_doc.spans["ruler"]) == 2
assert pred_doc.spans["ruler"][0].label_ == "FOOBAR"
assert pred_doc.spans["ruler"][1].label_ == "BARBAZ"
ref_doc = nlp.make_doc(text)
ref_doc.spans["ruler"] = [Span(ref_doc, 0, 2, label="FOOBAR")]
scores = nlp.evaluate([Example(pred_doc, ref_doc)])
assert scores["spans_ruler_p"] == 0.5
assert scores["spans_ruler_r"] == 1.0
@pytest.mark.parametrize("n_process", [1, 2])
def test_span_ruler_multiprocessing(n_process):
if isinstance(get_current_ops, NumpyOps) or n_process < 2:
texts = ["I enjoy eating Pizza Hut pizza."]
patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut"}]
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
for doc in nlp.pipe(texts, n_process=2):
for ent in doc.spans["ruler"]:
assert ent.label_ == "FASTFOOD"
def test_span_ruler_serialize_dir(patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
with make_tempdir() as d:
ruler.to_disk(d / "test_ruler")
ruler.from_disk(d / "test_ruler") # read from an existing directory
with pytest.raises(ValueError):
ruler.from_disk(d / "non_existing_dir") # read from a bad directory
def test_span_ruler_remove_basic(person_org_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(person_org_patterns)
doc = ruler(nlp.make_doc("Dina went to school"))
assert len(ruler.patterns) == 3
assert len(doc.spans["ruler"]) == 1
assert doc.spans["ruler"][0].label_ == "PERSON"
assert doc.spans["ruler"][0].text == "Dina"
ruler.remove("PERSON")
doc = ruler(nlp.make_doc("Dina went to school"))
assert len(doc.spans["ruler"]) == 0
assert len(ruler.patterns) == 2
def test_span_ruler_remove_nonexisting_pattern(person_org_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(person_org_patterns)
assert len(ruler.patterns) == 3
with pytest.raises(ValueError):
ruler.remove("NE")
with pytest.raises(ValueError):
ruler.remove_by_id("NE")
def test_span_ruler_remove_several_patterns(person_org_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(person_org_patterns)
doc = ruler(nlp.make_doc("Dina founded the company ACME."))
assert len(ruler.patterns) == 3
assert len(doc.spans["ruler"]) == 2
assert doc.spans["ruler"][0].label_ == "PERSON"
assert doc.spans["ruler"][0].text == "Dina"
assert doc.spans["ruler"][1].label_ == "ORG"
assert doc.spans["ruler"][1].text == "ACME"
ruler.remove("PERSON")
doc = ruler(nlp.make_doc("Dina founded the company ACME"))
assert len(ruler.patterns) == 2
assert len(doc.spans["ruler"]) == 1
assert doc.spans["ruler"][0].label_ == "ORG"
assert doc.spans["ruler"][0].text == "ACME"
ruler.remove("ORG")
with pytest.warns(UserWarning):
doc = ruler(nlp.make_doc("Dina founded the company ACME"))
assert len(ruler.patterns) == 0
assert len(doc.spans["ruler"]) == 0
def test_span_ruler_remove_patterns_in_a_row(person_org_date_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(person_org_date_patterns)
doc = ruler(nlp.make_doc("Dina founded the company ACME on June 14th"))
assert len(doc.spans["ruler"]) == 3
assert doc.spans["ruler"][0].label_ == "PERSON"
assert doc.spans["ruler"][0].text == "Dina"
assert doc.spans["ruler"][1].label_ == "ORG"
assert doc.spans["ruler"][1].text == "ACME"
assert doc.spans["ruler"][2].label_ == "DATE"
assert doc.spans["ruler"][2].text == "June 14th"
ruler.remove("ORG")
ruler.remove("DATE")
doc = ruler(nlp.make_doc("Dina went to school"))
assert len(doc.spans["ruler"]) == 1
def test_span_ruler_remove_all_patterns(person_org_date_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(person_org_date_patterns)
assert len(ruler.patterns) == 4
ruler.remove("PERSON")
assert len(ruler.patterns) == 3
ruler.remove("ORG")
assert len(ruler.patterns) == 1
ruler.remove("DATE")
assert len(ruler.patterns) == 0
with pytest.warns(UserWarning):
doc = ruler(nlp.make_doc("Dina founded the company ACME on June 14th"))
assert len(doc.spans["ruler"]) == 0
def test_span_ruler_remove_and_add():
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler")
patterns1 = [{"label": "DATE1", "pattern": "last time"}]
ruler.add_patterns(patterns1)
doc = ruler(
nlp.make_doc("I saw him last time we met, this time he brought some flowers")
)
assert len(ruler.patterns) == 1
assert len(doc.spans["ruler"]) == 1
assert doc.spans["ruler"][0].label_ == "DATE1"
assert doc.spans["ruler"][0].text == "last time"
patterns2 = [{"label": "DATE2", "pattern": "this time"}]
ruler.add_patterns(patterns2)
doc = ruler(
nlp.make_doc("I saw him last time we met, this time he brought some flowers")
)
assert len(ruler.patterns) == 2
assert len(doc.spans["ruler"]) == 2
assert doc.spans["ruler"][0].label_ == "DATE1"
assert doc.spans["ruler"][0].text == "last time"
assert doc.spans["ruler"][1].label_ == "DATE2"
assert doc.spans["ruler"][1].text == "this time"
ruler.remove("DATE1")
doc = ruler(
nlp.make_doc("I saw him last time we met, this time he brought some flowers")
)
assert len(ruler.patterns) == 1
assert len(doc.spans["ruler"]) == 1
assert doc.spans["ruler"][0].label_ == "DATE2"
assert doc.spans["ruler"][0].text == "this time"
ruler.add_patterns(patterns1)
doc = ruler(
nlp.make_doc("I saw him last time we met, this time he brought some flowers")
)
assert len(ruler.patterns) == 2
assert len(doc.spans["ruler"]) == 2
patterns3 = [{"label": "DATE3", "pattern": "another time"}]
ruler.add_patterns(patterns3)
doc = ruler(
nlp.make_doc(
"I saw him last time we met, this time he brought some flowers, another time some chocolate."
)
)
assert len(ruler.patterns) == 3
assert len(doc.spans["ruler"]) == 3
ruler.remove("DATE3")
doc = ruler(
nlp.make_doc(
"I saw him last time we met, this time he brought some flowers, another time some chocolate."
)
)
assert len(ruler.patterns) == 2
assert len(doc.spans["ruler"]) == 2
def test_span_ruler_spans_filter(overlapping_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe(
"span_ruler",
config={"spans_filter": {"@misc": "spacy.first_longest_spans_filter.v1"}},
)
ruler.add_patterns(overlapping_patterns)
doc = ruler(nlp.make_doc("foo bar baz"))
assert len(doc.spans["ruler"]) == 1
assert doc.spans["ruler"][0].label_ == "FOOBAR"
def test_span_ruler_ents_default_filter(overlapping_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe("span_ruler", config={"annotate_ents": True})
ruler.add_patterns(overlapping_patterns)
doc = ruler(nlp.make_doc("foo bar baz"))
assert len(doc.ents) == 1
assert doc.ents[0].label_ == "FOOBAR"
def test_span_ruler_ents_overwrite_filter(overlapping_patterns):
nlp = spacy.blank("xx")
ruler = nlp.add_pipe(
"span_ruler",
config={
"annotate_ents": True,
"overwrite": False,
"ents_filter": {"@misc": "spacy.prioritize_new_ents_filter.v1"},
},
)
ruler.add_patterns(overlapping_patterns)
# overlapping ents are clobbered, non-overlapping ents are preserved
doc = nlp.make_doc("foo bar baz a b c")
doc.ents = [Span(doc, 1, 3, label="BARBAZ"), Span(doc, 3, 6, label="ABC")]
doc = ruler(doc)
assert len(doc.ents) == 2
assert doc.ents[0].label_ == "FOOBAR"
assert doc.ents[1].label_ == "ABC"
def test_span_ruler_ents_bad_filter(overlapping_patterns):
@registry.misc("test_pass_through_filter")
def make_pass_through_filter():
def pass_through_filter(spans1, spans2):
return spans1 + spans2
return pass_through_filter
nlp = spacy.blank("xx")
ruler = nlp.add_pipe(
"span_ruler",
config={
"annotate_ents": True,
"ents_filter": {"@misc": "test_pass_through_filter"},
},
)
ruler.add_patterns(overlapping_patterns)
with pytest.raises(ValueError):
ruler(nlp.make_doc("foo bar baz"))

161
spacy/tests/serialize/test_serialize_span_groups.py Normal file
View File

@ -0,0 +1,161 @@
import pytest
from spacy.tokens import Span, SpanGroup
from spacy.tokens._dict_proxies import SpanGroups
@pytest.mark.issue(10685)
def test_issue10685(en_tokenizer):
"""Test `SpanGroups` de/serialization"""
# Start with a Doc with no SpanGroups
doc = en_tokenizer("Will it blend?")
# Test empty `SpanGroups` de/serialization:
assert len(doc.spans) == 0
doc.spans.from_bytes(doc.spans.to_bytes())
assert len(doc.spans) == 0
# Test non-empty `SpanGroups` de/serialization:
doc.spans["test"] = SpanGroup(doc, name="test", spans=[doc[0:1]])
doc.spans["test2"] = SpanGroup(doc, name="test", spans=[doc[1:2]])
def assert_spangroups():
assert len(doc.spans) == 2
assert doc.spans["test"].name == "test"
assert doc.spans["test2"].name == "test"
assert list(doc.spans["test"]) == [doc[0:1]]
assert list(doc.spans["test2"]) == [doc[1:2]]
# Sanity check the currently-expected behavior
assert_spangroups()
# Now test serialization/deserialization:
doc.spans.from_bytes(doc.spans.to_bytes())
assert_spangroups()
def test_span_groups_serialization_mismatches(en_tokenizer):
"""Test the serialization of multiple mismatching `SpanGroups` keys and `SpanGroup.name`s"""
doc = en_tokenizer("How now, brown cow?")
# Some variety:
# 1 SpanGroup where its name matches its key
# 2 SpanGroups that have the same name--which is not a key
# 2 SpanGroups that have the same name--which is a key
# 1 SpanGroup that is a value for 2 different keys (where its name is a key)
# 1 SpanGroup that is a value for 2 different keys (where its name is not a key)
groups = doc.spans
groups["key1"] = SpanGroup(doc, name="key1", spans=[doc[0:1], doc[1:2]])
groups["key2"] = SpanGroup(doc, name="too", spans=[doc[3:4], doc[4:5]])
groups["key3"] = SpanGroup(doc, name="too", spans=[doc[1:2], doc[0:1]])
groups["key4"] = SpanGroup(doc, name="key4", spans=[doc[0:1]])
groups["key5"] = SpanGroup(doc, name="key4", spans=[doc[0:1]])
sg6 = SpanGroup(doc, name="key6", spans=[doc[0:1]])
groups["key6"] = sg6
groups["key7"] = sg6
sg8 = SpanGroup(doc, name="also", spans=[doc[1:2]])
groups["key8"] = sg8
groups["key9"] = sg8
regroups = SpanGroups(doc).from_bytes(groups.to_bytes())
# Assert regroups == groups
assert regroups.keys() == groups.keys()
for key, regroup in regroups.items():
# Assert regroup == groups[key]
assert regroup.name == groups[key].name
assert list(regroup) == list(groups[key])
@pytest.mark.parametrize(
"spans_bytes,doc_text,expected_spangroups,expected_warning",
# The bytestrings below were generated from an earlier version of spaCy
# that serialized `SpanGroups` as a list of SpanGroup bytes (via SpanGroups.to_bytes).
# Comments preceding the bytestrings indicate from what Doc they were created.
[
# Empty SpanGroups:
(b"\x90", "", {}, False),
# doc = nlp("Will it blend?")
# doc.spans['test'] = SpanGroup(doc, name='test', spans=[doc[0:1]])
(
b"\x91\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x04",
"Will it blend?",
{"test": {"name": "test", "spans": [(0, 1)]}},
False,
),
# doc = nlp("Will it blend?")
# doc.spans['test'] = SpanGroup(doc, name='test', spans=[doc[0:1]])
# doc.spans['test2'] = SpanGroup(doc, name='test', spans=[doc[1:2]])
(
b"\x92\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x04\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x05\x00\x00\x00\x07",
"Will it blend?",
# We expect only 1 SpanGroup to be in doc.spans in this example
# because there are 2 `SpanGroup`s that have the same .name. See #10685.
{"test": {"name": "test", "spans": [(1, 2)]}},
True,
),
# doc = nlp('How now, brown cow?')
# doc.spans['key1'] = SpanGroup(doc, name='key1', spans=[doc[0:1], doc[1:2]])
# doc.spans['key2'] = SpanGroup(doc, name='too', spans=[doc[3:4], doc[4:5]])
# doc.spans['key3'] = SpanGroup(doc, name='too', spans=[doc[1:2], doc[0:1]])
# doc.spans['key4'] = SpanGroup(doc, name='key4', spans=[doc[0:1]])
# doc.spans['key5'] = SpanGroup(doc, name='key4', spans=[doc[0:1]])
(
b"\x95\xc4m\x83\xa4name\xa4key1\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x04\x00\x00\x00\x07\xc4l\x83\xa4name\xa3too\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x04\x00\x00\x00\t\x00\x00\x00\x0e\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x05\x00\x00\x00\x0f\x00\x00\x00\x12\xc4l\x83\xa4name\xa3too\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x04\x00\x00\x00\x07\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4C\x83\xa4name\xa4key4\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4C\x83\xa4name\xa4key4\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03",
"How now, brown cow?",
{
"key1": {"name": "key1", "spans": [(0, 1), (1, 2)]},
"too": {"name": "too", "spans": [(1, 2), (0, 1)]},
"key4": {"name": "key4", "spans": [(0, 1)]},
},
True,
),
],
)
def test_deserialize_span_groups_compat(
en_tokenizer, spans_bytes, doc_text, expected_spangroups, expected_warning
):
"""Test backwards-compatibility of `SpanGroups` deserialization.
This uses serializations (bytes) from a prior version of spaCy (before 3.3.1).
spans_bytes (bytes): Serialized `SpanGroups` object.
doc_text (str): Doc text.
expected_spangroups (dict):
Dict mapping every expected (after deserialization) `SpanGroups` key
to a SpanGroup's "args", where a SpanGroup's args are given as a dict:
{"name": span_group.name,
"spans": [(span0.start, span0.end), ...]}
expected_warning (bool): Whether a warning is to be expected from .from_bytes()
--i.e. if more than 1 SpanGroup has the same .name within the `SpanGroups`.
"""
doc = en_tokenizer(doc_text)
if expected_warning:
with pytest.warns(UserWarning):
doc.spans.from_bytes(spans_bytes)
else:
# TODO: explicitly check for lack of a warning
doc.spans.from_bytes(spans_bytes)
assert doc.spans.keys() == expected_spangroups.keys()
for name, spangroup_args in expected_spangroups.items():
assert doc.spans[name].name == spangroup_args["name"]
spans = [Span(doc, start, end) for start, end in spangroup_args["spans"]]
assert list(doc.spans[name]) == spans
def test_span_groups_serialization(en_tokenizer):
doc = en_tokenizer("0 1 2 3 4 5 6")
span_groups = SpanGroups(doc)
spans = [doc[0:2], doc[1:3]]
sg1 = SpanGroup(doc, spans=spans)
span_groups["key1"] = sg1
span_groups["key2"] = sg1
span_groups["key3"] = []
reloaded_span_groups = SpanGroups(doc).from_bytes(span_groups.to_bytes())
assert span_groups.keys() == reloaded_span_groups.keys()
for key, value in span_groups.items():
assert all(
span == reloaded_span
for span, reloaded_span in zip(span_groups[key], reloaded_span_groups[key])
)

53
spacy/tokens/_dict_proxies.py
View File

@ -1,10 +1,11 @@
from typing import Iterable, Tuple, Union, Optional, TYPE_CHECKING
from typing import Dict, Iterable, List, Tuple, Union, Optional, TYPE_CHECKING
import warnings
import weakref
from collections import UserDict
import srsly
from .span_group import SpanGroup
from ..errors import Errors
from ..errors import Errors, Warnings
if TYPE_CHECKING:
@ -16,7 +17,7 @@ if TYPE_CHECKING:
# Why inherit from UserDict instead of dict here?
# Well, the 'dict' class doesn't necessarily delegate everything nicely,
# for performance reasons. The UserDict is slower but better behaved.
# See https://treyhunner.com/2019/04/why-you-shouldnt-inherit-from-list-and-dict-in-python/0ww
# See https://treyhunner.com/2019/04/why-you-shouldnt-inherit-from-list-and-dict-in-python/
class SpanGroups(UserDict):
"""A dict-like proxy held by the Doc, to control access to span groups."""
@ -53,20 +54,52 @@ class SpanGroups(UserDict):
return super().setdefault(key, default=default)
def to_bytes(self) -> bytes:
# We don't need to serialize this as a dict, because the groups
# know their names.
# We serialize this as a dict in order to track the key(s) a SpanGroup
# is a value of (in a backward- and forward-compatible way), since
# a SpanGroup can have a key that doesn't match its `.name` (See #10685)
if len(self) == 0:
return self._EMPTY_BYTES
msg = [value.to_bytes() for value in self.values()]
msg: Dict[bytes, List[str]] = {}
for key, value in self.items():
msg.setdefault(value.to_bytes(), []).append(key)
return srsly.msgpack_dumps(msg)
def from_bytes(self, bytes_data: bytes) -> "SpanGroups":
msg = [] if bytes_data == self._EMPTY_BYTES else srsly.msgpack_loads(bytes_data)
# backwards-compatibility: bytes_data may be one of:
# b'', a serialized empty list, a serialized list of SpanGroup bytes
# or a serialized dict of SpanGroup bytes -> keys
msg = (
[]
if not bytes_data or bytes_data == self._EMPTY_BYTES
else srsly.msgpack_loads(bytes_data)
)
self.clear()
doc = self._ensure_doc()
for value_bytes in msg:
group = SpanGroup(doc).from_bytes(value_bytes)
self[group.name] = group
if isinstance(msg, list):
# This is either the 1st version of `SpanGroups` serialization
# or there were no SpanGroups serialized
for value_bytes in msg:
group = SpanGroup(doc).from_bytes(value_bytes)
if group.name in self:
# Display a warning if `msg` contains `SpanGroup`s
# that have the same .name (attribute).
# Because, for `SpanGroups` serialized as lists,
# only 1 SpanGroup per .name is loaded. (See #10685)
warnings.warn(
Warnings.W120.format(
group_name=group.name, group_values=self[group.name]
)
)
self[group.name] = group
else:
for value_bytes, keys in msg.items():
group = SpanGroup(doc).from_bytes(value_bytes)
# Deserialize `SpanGroup`s as copies because it's possible for two
# different `SpanGroup`s (pre-serialization) to have the same bytes
# (since they can have the same `.name`).
self[keys[0]] = group
for key in keys[1:]:
self[key] = group.copy()
return self
def _ensure_doc(self) -> "Doc":

3
spacy/tokens/doc.pyi
View File

@ -170,6 +170,9 @@ class Doc:
def extend_tensor(self, tensor: Floats2d) -> None: ...
def retokenize(self) -> Retokenizer: ...
def to_json(self, underscore: Optional[List[str]] = ...) -> Dict[str, Any]: ...
def from_json(
self, doc_json: Dict[str, Any] = ..., validate: bool = False
) -> Doc: ...
def to_utf8_array(self, nr_char: int = ...) -> Ints2d: ...
@staticmethod
def _get_array_attrs() -> Tuple[Any]: ...

184
spacy/tokens/doc.pyx
View File

@ -1,4 +1,6 @@
# cython: infer_types=True, bounds_check=False, profile=True
from typing import Set
cimport cython
cimport numpy as np
from libc.string cimport memcpy
@ -31,10 +33,11 @@ from ..errors import Errors, Warnings
from ..morphology import Morphology
from .. import util
from .. import parts_of_speech
from .. import schemas
from .underscore import Underscore, get_ext_args
from ._retokenize import Retokenizer
from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
from ..util import get_words_and_spaces
DEF PADDING = 5
@ -516,7 +519,7 @@ cdef class Doc:
def doc(self):
return self
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict"):
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
"""Create a `Span` object from the slice
`doc.text[start_idx : end_idx]`. Returns None if no valid `Span` can be
created.
@ -575,7 +578,7 @@ cdef class Doc:
start += 1
# Currently we have the token index, we want the range-end index
end += 1
cdef Span span = Span(self, start, end, label=label, kb_id=kb_id, vector=vector)
cdef Span span = Span(self, start, end, label=label, kb_id=kb_id, span_id=span_id, vector=vector)
return span
def similarity(self, other):
@ -713,6 +716,7 @@ cdef class Doc:
cdef int start = -1
cdef attr_t label = 0
cdef attr_t kb_id = 0
cdef attr_t ent_id = 0
output = []
for i in range(self.length):
token = &self.c[i]
@ -723,18 +727,20 @@ cdef class Doc:
elif token.ent_iob == 2 or token.ent_iob == 0 or \
(token.ent_iob == 3 and token.ent_type == 0):
if start != -1:
output.append(Span(self, start, i, label=label, kb_id=kb_id))
output.append(Span(self, start, i, label=label, kb_id=kb_id, span_id=ent_id))
start = -1
label = 0
kb_id = 0
ent_id = 0
elif token.ent_iob == 3:
if start != -1:
output.append(Span(self, start, i, label=label, kb_id=kb_id))
output.append(Span(self, start, i, label=label, kb_id=kb_id, span_id=ent_id))
start = i
label = token.ent_type
kb_id = token.ent_kb_id
ent_id = token.ent_id
if start != -1:
output.append(Span(self, start, self.length, label=label, kb_id=kb_id))
output.append(Span(self, start, self.length, label=label, kb_id=kb_id, span_id=ent_id))
# remove empty-label spans
output = [o for o in output if o.label_ != ""]
return tuple(output)
@ -743,14 +749,14 @@ 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
cdef attr_t entity_type, kb_id, ent_id
cdef int ent_start, ent_end
ent_spans = []
for ent_info in ents:
entity_type_, kb_id, ent_start, ent_end = get_entity_info(ent_info)
entity_type_, kb_id, ent_start, ent_end, ent_id = get_entity_info(ent_info)
if isinstance(entity_type_, str):
self.vocab.strings.add(entity_type_)
span = Span(self, ent_start, ent_end, label=entity_type_, kb_id=kb_id)
span = Span(self, ent_start, ent_end, label=entity_type_, kb_id=kb_id, span_id=ent_id)
ent_spans.append(span)
self.set_ents(ent_spans, default=SetEntsDefault.outside)
@ -801,6 +807,9 @@ cdef class Doc:
self.c[i].ent_iob = 1
self.c[i].ent_type = span.label
self.c[i].ent_kb_id = span.kb_id
# for backwards compatibility in v3, only set ent_id from
# span.id if it's set, otherwise don't override
self.c[i].ent_id = span.id if span.id else self.c[i].ent_id
for span in blocked:
for i in range(span.start, span.end):
self.c[i].ent_iob = 3
@ -1180,6 +1189,7 @@ cdef class Doc:
span.end_char + char_offset,
span.label,
span.kb_id,
span.id,
span.text, # included as a check
))
char_offset += len(doc.text)
@ -1215,8 +1225,9 @@ cdef class Doc:
span_tuple[1],
label=span_tuple[2],
kb_id=span_tuple[3],
span_id=span_tuple[4],
)
text = span_tuple[4]
text = span_tuple[5]
if span is not None and span.text == text:
concat_doc.spans[key].append(span)
else:
@ -1467,6 +1478,138 @@ cdef class Doc:
remove_label_if_necessary(attributes[i])
retokenizer.merge(span, attributes[i])
def from_json(self, doc_json, *, validate=False):
"""Convert a JSON document generated by Doc.to_json() to a Doc.
doc_json (Dict): JSON representation of doc object to load.
validate (bool): Whether to validate `doc_json` against the expected schema.
Defaults to False.
RETURNS (Doc): A doc instance corresponding to the specified JSON representation.
"""
if validate:
schema_validation_message = schemas.validate(schemas.DocJSONSchema, doc_json)
if schema_validation_message:
raise ValueError(Errors.E1038.format(message=schema_validation_message))
### Token-level properties ###
words = []
token_attrs_ids = (POS, HEAD, DEP, LEMMA, TAG, MORPH)
# Map annotation type IDs to their string equivalents.
token_attrs = {t: self.vocab.strings[t].lower() for t in token_attrs_ids}
token_annotations = {}
# Gather token-level properties.
for token_json in doc_json["tokens"]:
words.append(doc_json["text"][token_json["start"]:token_json["end"]])
for attr, attr_json in token_attrs.items():
if attr_json in token_json:
if token_json["id"] == 0 and attr not in token_annotations:
token_annotations[attr] = []
elif attr not in token_annotations:
raise ValueError(Errors.E1040.format(partial_attrs=attr))
token_annotations[attr].append(token_json[attr_json])
# Initialize doc instance.
start = 0
cdef const LexemeC* lex
cdef bint has_space
reconstructed_words, spaces = get_words_and_spaces(words, doc_json["text"])
assert words == reconstructed_words
for word, has_space in zip(words, spaces):
lex = self.vocab.get(self.mem, word)
self.push_back(lex, has_space)
# Set remaining token-level attributes via Doc.from_array().
if HEAD in token_annotations:
token_annotations[HEAD] = [
head - i for i, head in enumerate(token_annotations[HEAD])
]
if DEP in token_annotations and HEAD not in token_annotations:
token_annotations[HEAD] = [0] * len(token_annotations[DEP])
if HEAD in token_annotations and DEP not in token_annotations:
raise ValueError(Errors.E1017)
if POS in token_annotations:
for pp in set(token_annotations[POS]):
if pp not in parts_of_speech.IDS:
raise ValueError(Errors.E1021.format(pp=pp))
# Collect token attributes, assert all tokens have exactly the same set of attributes.
attrs = []
partial_attrs: Set[str] = set()
for attr in token_attrs.keys():
if attr in token_annotations:
if len(token_annotations[attr]) != len(words):
partial_attrs.add(token_attrs[attr])
attrs.append(attr)
if len(partial_attrs):
raise ValueError(Errors.E1040.format(partial_attrs=partial_attrs))
# If there are any other annotations, set them.
if attrs:
array = self.to_array(attrs)
if array.ndim == 1:
array = numpy.reshape(array, (array.size, 1))
j = 0
for j, (attr, annot) in enumerate(token_annotations.items()):
if attr is HEAD:
for i in range(len(words)):
array[i, j] = annot[i]
elif attr is MORPH:
for i in range(len(words)):
array[i, j] = self.vocab.morphology.add(annot[i])
else:
for i in range(len(words)):
array[i, j] = self.vocab.strings.add(annot[i])
self.from_array(attrs, array)
### Span/document properties ###
# Complement other document-level properties (cats, spans, ents).
self.cats = doc_json.get("cats", {})
# Set sentence boundaries, if dependency parser not available but sentences are specified in JSON.
if not self.has_annotation("DEP"):
for sent in doc_json.get("sents", {}):
char_span = self.char_span(sent["start"], sent["end"])
if char_span is None:
raise ValueError(Errors.E1039.format(obj="sentence", start=sent["start"], end=sent["end"]))
char_span[0].is_sent_start = True
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]:
char_span = self.char_span(span["start"], span["end"], span["label"], span["kb_id"])
if char_span is None:
raise ValueError(Errors.E1039.format(obj="span", start=span["start"], end=span["end"]))
spans.append(char_span)
self.spans[span_group] = spans
if "ents" in doc_json:
ents = []
for ent in doc_json["ents"]:
char_span = self.char_span(ent["start"], ent["end"], ent["label"])
if char_span is None:
raise ValueError(Errors.E1039.format(obj="entity"), start=ent["start"], end=ent["end"])
ents.append(char_span)
self.ents = ents
# Add custom attributes. Note that only Doc extensions are currently considered, Token and Span extensions are
# not yet supported.
for attr in doc_json.get("_", {}):
if not Doc.has_extension(attr):
Doc.set_extension(attr)
self._.set(attr, doc_json["_"][attr])
return self
def to_json(self, underscore=None):
"""Convert a Doc to JSON.
@ -1477,12 +1620,10 @@ cdef class Doc:
"""
data = {"text": self.text}
if self.has_annotation("ENT_IOB"):
data["ents"] = [{"start": ent.start_char, "end": ent.end_char,
"label": ent.label_} for ent in self.ents]
data["ents"] = [{"start": ent.start_char, "end": ent.end_char, "label": ent.label_} for ent in self.ents]
if self.has_annotation("SENT_START"):
sents = list(self.sents)
data["sents"] = [{"start": sent.start_char, "end": sent.end_char}
for sent in sents]
data["sents"] = [{"start": sent.start_char, "end": sent.end_char} for sent in sents]
if self.cats:
data["cats"] = self.cats
data["tokens"] = []
@ -1508,7 +1649,9 @@ cdef class Doc:
for span_group in self.spans:
data["spans"][span_group] = []
for span in self.spans[span_group]:
span_data = {"start": span.start_char, "end": span.end_char, "label": span.label_, "kb_id": span.kb_id_}
span_data = {
"start": span.start_char, "end": span.end_char, "label": span.label_, "kb_id": span.kb_id_
}
data["spans"][span_group].append(span_data)
if underscore:
@ -1737,18 +1880,17 @@ cdef int [:,:] _get_lca_matrix(Doc doc, int start, int end):
def pickle_doc(doc):
bytes_data = doc.to_bytes(exclude=["vocab", "user_data", "user_hooks"])
hooks_and_data = (doc.user_data, doc.user_hooks, doc.user_span_hooks,
doc.user_token_hooks, doc._context)
doc.user_token_hooks)
return (unpickle_doc, (doc.vocab, srsly.pickle_dumps(hooks_and_data), bytes_data))
def unpickle_doc(vocab, hooks_and_data, bytes_data):
user_data, doc_hooks, span_hooks, token_hooks, _context = srsly.pickle_loads(hooks_and_data)
user_data, doc_hooks, span_hooks, token_hooks = srsly.pickle_loads(hooks_and_data)
doc = Doc(vocab, user_data=user_data).from_bytes(bytes_data, exclude=["user_data"])
doc.user_hooks.update(doc_hooks)
doc.user_span_hooks.update(span_hooks)
doc.user_token_hooks.update(token_hooks)
doc._context = _context
return doc
@ -1772,16 +1914,18 @@ def fix_attributes(doc, attributes):
def get_entity_info(ent_info):
ent_kb_id = 0
ent_id = 0
if isinstance(ent_info, Span):
ent_type = ent_info.label
ent_kb_id = ent_info.kb_id
start = ent_info.start
end = ent_info.end
ent_id = ent_info.id
elif len(ent_info) == 3:
ent_type, start, end = ent_info
ent_kb_id = 0
elif len(ent_info) == 4:
ent_type, ent_kb_id, start, end = ent_info
else:
ent_id, ent_kb_id, ent_type, start, end = ent_info
return ent_type, ent_kb_id, start, end
return ent_type, ent_kb_id, start, end, ent_id

3
spacy/tokens/span.pyi
View File

@ -48,7 +48,8 @@ class Span:
label: Union[str, int] = ...,
vector: Optional[Floats1d] = ...,
vector_norm: Optional[float] = ...,
kb_id: Optional[int] = ...,
kb_id: Union[str, int] = ...,
span_id: Union[str, int] = ...,
) -> None: ...
def __richcmp__(self, other: Span, op: int) -> bool: ...
def __hash__(self) -> int: ...

37
spacy/tokens/span.pyx
View File

@ -80,17 +80,20 @@ cdef class Span:
return Underscore.span_extensions.pop(name)
def __cinit__(self, Doc doc, int start, int end, label=0, vector=None,
vector_norm=None, kb_id=0):
vector_norm=None, kb_id=0, span_id=0):
"""Create a `Span` object from the slice `doc[start : end]`.
doc (Doc): The parent document.
start (int): The index of the first token of the span.
end (int): The index of the first token after the span.
label (int or str): A label to attach to the Span, e.g. for named entities.
label (Union[int, str]): A label to attach to the Span, e.g. for named
entities.
vector (ndarray[ndim=1, dtype='float32']): A meaning representation
of the span.
vector_norm (float): The L2 norm of the span's vector representation.
kb_id (uint64): An identifier from a Knowledge Base to capture the meaning of a named entity.
kb_id (Union[int, str]): An identifier from a Knowledge Base to capture
the meaning of a named entity.
span_id (Union[int, str]): An identifier to associate with the span.
DOCS: https://spacy.io/api/span#init
"""
@ -101,6 +104,8 @@ cdef class Span:
label = doc.vocab.strings.add(label)
if isinstance(kb_id, str):
kb_id = doc.vocab.strings.add(kb_id)
if isinstance(span_id, str):
span_id = doc.vocab.strings.add(span_id)
if label not in doc.vocab.strings:
raise ValueError(Errors.E084.format(label=label))
@ -112,6 +117,7 @@ cdef class Span:
self.c = SpanC(
label=label,
kb_id=kb_id,
id=span_id,
start=start,
end=end,
start_char=start_char,
@ -126,8 +132,8 @@ cdef class Span:
return False
else:
return True
self_tuple = (self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.doc)
other_tuple = (other.c.start_char, other.c.end_char, other.c.label, other.c.kb_id, other.doc)
self_tuple = (self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.id, self.doc)
other_tuple = (other.c.start_char, other.c.end_char, other.c.label, other.c.kb_id, other.id, other.doc)
# <
if op == 0:
return self_tuple < other_tuple
@ -148,7 +154,7 @@ cdef class Span:
return self_tuple >= other_tuple
def __hash__(self):
return hash((self.doc, self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id))
return hash((self.doc, self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.c.id))
def __len__(self):
"""Get the number of tokens in the span.
@ -632,7 +638,7 @@ cdef class Span:
else:
return self.doc[root]
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None):
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0):
"""Create a `Span` object from the slice `span.text[start : end]`.
start (int): The index of the first character of the span.
@ -774,6 +780,13 @@ cdef class Span:
def __set__(self, attr_t kb_id):
self.c.kb_id = kb_id
property id:
def __get__(self):
return self.c.id
def __set__(self, attr_t id):
self.c.id = id
property ent_id:
"""RETURNS (uint64): The entity ID."""
def __get__(self):
@ -812,13 +825,21 @@ cdef class Span:
self.label = self.doc.vocab.strings.add(label_)
property kb_id_:
"""RETURNS (str): The named entity's KB ID."""
"""RETURNS (str): The span's KB ID."""
def __get__(self):
return self.doc.vocab.strings[self.kb_id]
def __set__(self, str kb_id_):
self.kb_id = self.doc.vocab.strings.add(kb_id_)
property id_:
"""RETURNS (str): The span's ID."""
def __get__(self):
return self.doc.vocab.strings[self.id]
def __set__(self, str id_):
self.id = self.doc.vocab.strings.add(id_)
cdef int _count_words_to_root(const TokenC* token, int sent_length) except -1:
# Don't allow spaces to be the root, if there are

1
spacy/tokens/span_group.pyi
View File

@ -24,3 +24,4 @@ class SpanGroup:
def __getitem__(self, i: int) -> Span: ...
def to_bytes(self) -> bytes: ...
def from_bytes(self, bytes_data: bytes) -> SpanGroup: ...
def copy(self) -> SpanGroup: ...

9
spacy/util.py
View File

@ -1241,6 +1241,15 @@ def filter_spans(spans: Iterable["Span"]) -> List["Span"]:
return result
def filter_chain_spans(*spans: Iterable["Span"]) -> List["Span"]:
return filter_spans(itertools.chain(*spans))
@registry.misc("spacy.first_longest_spans_filter.v1")
def make_first_longest_spans_filter():
return filter_chain_spans
def to_bytes(getters: Dict[str, Callable[[], bytes]], exclude: Iterable[str]) -> bytes:
return srsly.msgpack_dumps(to_dict(getters, exclude))

39
website/docs/api/doc.md
View File

@ -481,6 +481,45 @@ Deserialize, i.e. import the document contents from a binary string.
| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The `Doc` object. ~~Doc~~ |
## Doc.to_json {#to_json tag="method"}
Serializes a document to JSON. Note that this is format differs from the
deprecated [`JSON training format`](/api/data-formats#json-input).
> #### Example
>
> ```python
> doc = nlp("All we have to decide is what to do with the time that is given us.")
> assert doc.to_json()["text"] == doc.text
> ```
| Name | Description |
| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `underscore` | Optional list of string names of custom `Doc` attributes. Attribute values need to be JSON-serializable. Values will be added to an `"_"` key in the data, e.g. `"_": {"foo": "bar"}`. ~~Optional[List[str]]~~ |
| **RETURNS** | The data in JSON format. ~~Dict[str, Any]~~ |
## Doc.from_json {#from_json tag="method" new="3.3.1"}
Deserializes a document from JSON, i.e. generates a document from the provided
JSON data as generated by [`Doc.to_json()`](/api/doc#to_json).
> #### Example
>
> ```python
> from spacy.tokens import Doc
> doc = nlp("All we have to decide is what to do with the time that is given us.")
> doc_json = doc.to_json()
> deserialized_doc = Doc(nlp.vocab).from_json(doc_json)
> assert deserialized_doc.text == doc.text == doc_json["text"]
> ```
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------- |
| `doc_json` | The Doc data in JSON format from [`Doc.to_json`](#to_json). ~~Dict[str, Any]~~ |
| _keyword-only_ | |
| `validate` | Whether to validate the JSON input against the expected schema for detailed debugging. Defaults to `False`. ~~bool~~ |
| **RETURNS** | A `Doc` corresponding to the provided JSON. ~~Doc~~ |
## Doc.retokenize {#retokenize tag="contextmanager" new="2.1"}
Context manager to handle retokenization of the `Doc`. Modifications to the

2
website/docs/api/entityruler.md
View File

@ -290,7 +290,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
>
> ```python
> ruler_bytes = ruler.to_bytes()
> ruler = nlp.add_pipe("enity_ruler")
> ruler = nlp.add_pipe("entity_ruler")
> ruler.from_bytes(ruler_bytes)
> ```

7
website/docs/api/span.md
View File

@ -27,6 +27,7 @@ Create a `Span` object from the slice `doc[start : end]`.
| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
| `vector_norm` | The L2 norm of the document's vector representation. ~~float~~ |
| `kb_id` | A knowledge base ID to attach to the span, e.g. for named entities. ~~Union[str, int]~~ |
| `span_id` | An ID to associate with the span. ~~Union[str, int]~~ |
## Span.\_\_getitem\_\_ {#getitem tag="method"}
@ -560,7 +561,9 @@ overlaps with will be returned.
| `lemma_` | The span's lemma. Equivalent to `"".join(token.text_with_ws for token in span)`. ~~str~~ |
| `kb_id` | The hash value of the knowledge base ID referred to by the span. ~~int~~ |
| `kb_id_` | The knowledge base ID referred to by the span. ~~str~~ |
| `ent_id` | The hash value of the named entity the token is an instance of. ~~int~~ |
| `ent_id_` | The string ID of the named entity the token is an instance of. ~~str~~ |
| `ent_id` | The hash value of the named entity the root token is an instance of. ~~int~~ |
| `ent_id_` | The string ID of the named entity the root token is an instance of. ~~str~~ |
| `id` | The hash value of the span's ID. ~~int~~ |
| `id_` | The span's ID. ~~str~~ |
| `sentiment` | A scalar value indicating the positivity or negativity of the span. ~~float~~ |
| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ |

351
website/docs/api/spanruler.md Normal file
View File

@ -0,0 +1,351 @@
---
title: SpanRuler
tag: class
source: spacy/pipeline/span_ruler.py
new: 3.3
teaser: 'Pipeline component for rule-based span and named entity recognition'
api_string_name: span_ruler
api_trainable: false
---
The span ruler lets you add spans to [`Doc.spans`](/api/doc#spans) and/or
[`Doc.ents`](/api/doc#ents) using token-based rules or exact phrase matches. For
usage examples, see the docs on
[rule-based span matching](/usage/rule-based-matching#spanruler).
## Assigned Attributes {#assigned-attributes}
Matches will be saved to `Doc.spans[spans_key]` as a
[`SpanGroup`](/api/spangroup) and/or to `Doc.ents`, where the annotation is
saved in the `Token.ent_type` and `Token.ent_iob` fields.
| Location | Value |
| ---------------------- | ----------------------------------------------------------------- |
| `Doc.spans[spans_key]` | The annotated spans. ~~SpanGroup~~ |
| `Doc.ents` | The annotated spans. ~~Tuple[Span]~~ |
| `Token.ent_iob` | An enum encoding of the IOB part of the named entity tag. ~~int~~ |
| `Token.ent_iob_` | The IOB part of the named entity tag. ~~str~~ |
| `Token.ent_type` | The label part of the named entity tag (hash). ~~int~~ |
| `Token.ent_type_` | The label part of the named entity tag. ~~str~~ |
## Config and implementation {#config}
The default config is defined by the pipeline component factory and describes
how the component should be configured. You can override its settings via the
`config` argument on [`nlp.add_pipe`](/api/language#add_pipe) or in your
[`config.cfg`](/usage/training#config).
> #### Example
>
> ```python
> config = {
> "spans_key": "my_spans",
> "validate": True,
> "overwrite": False,
> }
> nlp.add_pipe("span_ruler", config=config)
> ```
| Setting | Description |
| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `spans_key` | The spans key to save the spans under. If `None`, no spans are saved. Defaults to `"ruler"`. ~~Optional[str]~~ |
| `spans_filter` | The optional method to filter spans before they are assigned to doc.spans. Defaults to `None`. ~~Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]]~~ |
| `annotate_ents` | Whether to save spans to doc.ents. Defaults to `False`. ~~bool~~ |
| `ents_filter` | The method to filter spans before they are assigned to doc.ents. Defaults to `util.filter_chain_spans`. ~~Callable[[Iterable[Span], Iterable[Span]], List[Span]]~~ |
| `phrase_matcher_attr` | Token attribute to match on, passed to the internal PhraseMatcher as `attr`. Defaults to `None`. ~~Optional[Union[int, str]]~~ |
| `validate` | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~ |
| `overwrite` | Whether to remove any existing spans under `Doc.spans[spans key]` if `spans_key` is set, or to remove any ents under `Doc.ents` if `annotate_ents` is set. Defaults to `True`. ~~bool~~ |
| `scorer` | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~ |
```python
%%GITHUB_SPACY/spacy/pipeline/span_ruler.py
```
## SpanRuler.\_\_init\_\_ {#init tag="method"}
Initialize the span ruler. If patterns are supplied here, they need to be a list
of dictionaries with a `"label"` and `"pattern"` key. A pattern can either be a
token pattern (list) or a phrase pattern (string). For example:
`{"label": "ORG", "pattern": "Apple"}`.
> #### Example
>
> ```python
> # Construction via add_pipe
> ruler = nlp.add_pipe("span_ruler")
>
> # Construction from class
> from spacy.pipeline import SpanRuler
> ruler = SpanRuler(nlp, overwrite=True)
> ```
| Name | Description |
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `nlp` | The shared nlp object to pass the vocab to the matchers and process phrase patterns. ~~Language~~ |
| `name` | Instance name of the current pipeline component. Typically passed in automatically from the factory when the component is added. Used to disable the current span ruler while creating phrase patterns with the nlp object. ~~str~~ |
| _keyword-only_ | |
| `spans_key` | The spans key to save the spans under. If `None`, no spans are saved. Defaults to `"ruler"`. ~~Optional[str]~~ |
| `spans_filter` | The optional method to filter spans before they are assigned to doc.spans. Defaults to `None`. ~~Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]]~~ |
| `annotate_ents` | Whether to save spans to doc.ents. Defaults to `False`. ~~bool~~ |
| `ents_filter` | The method to filter spans before they are assigned to doc.ents. Defaults to `util.filter_chain_spans`. ~~Callable[[Iterable[Span], Iterable[Span]], List[Span]]~~ |
| `phrase_matcher_attr` | Token attribute to match on, passed to the internal PhraseMatcher as `attr`. Defaults to `None`. ~~Optional[Union[int, str]]~~ |
| `validate` | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~ |
| `overwrite` | Whether to remove any existing spans under `Doc.spans[spans key]` if `spans_key` is set, or to remove any ents under `Doc.ents` if `annotate_ents` is set. Defaults to `True`. ~~bool~~ |
| `scorer` | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~ |
## SpanRuler.initialize {#initialize tag="method"}
Initialize the component with data and used before training to load in rules
from a [pattern file](/usage/rule-based-matching/#spanruler-files). This method
is typically called by [`Language.initialize`](/api/language#initialize) and
lets you customize arguments it receives via the
[`[initialize.components]`](/api/data-formats#config-initialize) block in the
config. Any existing patterns are removed on initialization.
> #### Example
>
> ```python
> span_ruler = nlp.add_pipe("span_ruler")
> span_ruler.initialize(lambda: [], nlp=nlp, patterns=patterns)
> ```
>
> ```ini
> ### config.cfg
> [initialize.components.span_ruler]
>
> [initialize.components.span_ruler.patterns]
> @readers = "srsly.read_jsonl.v1"
> path = "corpus/span_ruler_patterns.jsonl
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Not used by the `SpanRuler`. ~~Callable[[], Iterable[Example]]~~ |
| _keyword-only_ | |
| `nlp` | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~ |
| `patterns` | The list of patterns. Defaults to `None`. ~~Optional[Sequence[Dict[str, Union[str, List[Dict[str, Any]]]]]]~~ |
## SpanRuler.\_\len\_\_ {#len tag="method"}
The number of all patterns added to the span ruler.
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> assert len(ruler) == 0
> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
> assert len(ruler) == 1
> ```
| Name | Description |
| ----------- | ------------------------------- |
| **RETURNS** | The number of patterns. ~~int~~ |
## SpanRuler.\_\_contains\_\_ {#contains tag="method"}
Whether a label is present in the patterns.
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
> assert "ORG" in ruler
> assert not "PERSON" in ruler
> ```
| Name | Description |
| ----------- | --------------------------------------------------- |
| `label` | The label to check. ~~str~~ |
| **RETURNS** | Whether the span ruler contains the label. ~~bool~~ |
## SpanRuler.\_\_call\_\_ {#call tag="method"}
Find matches in the `Doc` and add them to `doc.spans[span_key]` and/or
`doc.ents`. Typically, this happens automatically after the component has been
added to the pipeline using [`nlp.add_pipe`](/api/language#add_pipe). If the
span ruler was initialized with `overwrite=True`, existing spans and entities
will be removed.
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
>
> doc = nlp("A text about Apple.")
> spans = [(span.text, span.label_) for span in doc.spans["ruler"]]
> assert spans == [("Apple", "ORG")]
> ```
| Name | Description |
| ----------- | -------------------------------------------------------------------- |
| `doc` | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
| **RETURNS** | The modified `Doc` with added spans/entities. ~~Doc~~ |
## SpanRuler.add_patterns {#add_patterns tag="method"}
Add patterns to the span ruler. A pattern can either be a token pattern (list of
dicts) or a phrase pattern (string). For more details, see the usage guide on
[rule-based matching](/usage/rule-based-matching).
> #### Example
>
> ```python
> patterns = [
> {"label": "ORG", "pattern": "Apple"},
> {"label": "GPE", "pattern": [{"lower": "san"}, {"lower": "francisco"}]}
> ]
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns(patterns)
> ```
| Name | Description |
| ---------- | ---------------------------------------------------------------- |
| `patterns` | The patterns to add. ~~List[Dict[str, Union[str, List[dict]]]]~~ |
## SpanRuler.remove {#remove tag="method"}
Remove patterns by label from the span ruler. A `ValueError` is raised if the
label does not exist in any patterns.
> #### Example
>
> ```python
> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns(patterns)
> ruler.remove("ORG")
> ```
| Name | Description |
| ------- | -------------------------------------- |
| `label` | The label of the pattern rule. ~~str~~ |
## SpanRuler.remove_by_id {#remove_by_id tag="method"}
Remove patterns by ID from the span ruler. A `ValueError` is raised if the ID
does not exist in any patterns.
> #### Example
>
> ```python
> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns(patterns)
> ruler.remove_by_id("apple")
> ```
| Name | Description |
| ------------ | ----------------------------------- |
| `pattern_id` | The ID of the pattern rule. ~~str~~ |
## SpanRuler.clear {#clear tag="method"}
Remove all patterns the span ruler.
> #### Example
>
> ```python
> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
> ruler = nlp.add_pipe("span_ruler")
> ruler.add_patterns(patterns)
> ruler.clear()
> ```
## SpanRuler.to_disk {#to_disk tag="method"}
Save the span ruler patterns to a directory. The patterns will be saved as
newline-delimited JSON (JSONL).
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> ruler.to_disk("/path/to/span_ruler")
> ```
| Name | Description |
| ------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
## SpanRuler.from_disk {#from_disk tag="method"}
Load the span ruler from a path.
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> ruler.from_disk("/path/to/span_ruler")
> ```
| Name | Description |
| ----------- | ----------------------------------------------------------------------------------------------- |
| `path` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
| **RETURNS** | The modified `SpanRuler` object. ~~SpanRuler~~ |
## SpanRuler.to_bytes {#to_bytes tag="method"}
Serialize the span ruler to a bytestring.
> #### Example
>
> ```python
> ruler = nlp.add_pipe("span_ruler")
> ruler_bytes = ruler.to_bytes()
> ```
| Name | Description |
| ----------- | ---------------------------------- |
| **RETURNS** | The serialized patterns. ~~bytes~~ |
## SpanRuler.from_bytes {#from_bytes tag="method"}
Load the pipe from a bytestring. Modifies the object in place and returns it.
> #### Example
>
> ```python
> ruler_bytes = ruler.to_bytes()
> ruler = nlp.add_pipe("span_ruler")
> ruler.from_bytes(ruler_bytes)
> ```
| Name | Description |
| ------------ | ---------------------------------------------- |
| `bytes_data` | The bytestring to load. ~~bytes~~ |
| **RETURNS** | The modified `SpanRuler` object. ~~SpanRuler~~ |
## SpanRuler.labels {#labels tag="property"}
All labels present in the match patterns.
| Name | Description |
| ----------- | -------------------------------------- |
| **RETURNS** | The string labels. ~~Tuple[str, ...]~~ |
## SpanRuler.ids {#ids tag="property"}
All IDs present in the `id` property of the match patterns.
| Name | Description |
| ----------- | ----------------------------------- |
| **RETURNS** | The string IDs. ~~Tuple[str, ...]~~ |
## SpanRuler.patterns {#patterns tag="property"}
All patterns that were added to the span ruler.
| Name | Description |
| ----------- | ---------------------------------------------------------------------------------------- |
| **RETURNS** | The original patterns, one dictionary per pattern. ~~List[Dict[str, Union[str, dict]]]~~ |
## Attributes {#attributes}
| Name | Description |
| ---------------- | -------------------------------------------------------------------------------- |
| `key` | The spans key that spans are saved under. ~~Optional[str]~~ |
| `matcher` | The underlying matcher used to process token patterns. ~~Matcher~~ |
| `phrase_matcher` | The underlying phrase matcher used to process phrase patterns. ~~PhraseMatcher~~ |

103
website/docs/usage/rule-based-matching.md
View File

@ -6,6 +6,7 @@ menu:
- ['Phrase Matcher', 'phrasematcher']
- ['Dependency Matcher', 'dependencymatcher']
- ['Entity Ruler', 'entityruler']
- ['Span Ruler', 'spanruler']
- ['Models & Rules', 'models-rules']
---
@ -1446,6 +1447,108 @@ with nlp.select_pipes(enable="tagger"):
ruler.add_patterns(patterns)
```
## Rule-based span matching {#spanruler new="3.3"}
The [`SpanRuler`](/api/spanruler) is a generalized version of the entity ruler
that lets you add spans to `doc.spans` or `doc.ents` based on pattern
dictionaries, which makes it easy to combine rule-based and statistical pipeline
components.
### Span patterns {#spanruler-patterns}
The [pattern format](#entityruler-patterns) is the same as for the entity ruler:
1. **Phrase patterns** for exact string matches (string).
```python
{"label": "ORG", "pattern": "Apple"}
```
2. **Token patterns** with one dictionary describing one token (list).
```python
{"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}
```
### Using the span ruler {#spanruler-usage}
The [`SpanRuler`](/api/spanruler) is a pipeline component that's typically added
via [`nlp.add_pipe`](/api/language#add_pipe). When the `nlp` object is called on
a text, it will find matches in the `doc` and add them as spans to
`doc.spans["ruler"]`, using the specified pattern label as the entity label.
Unlike in `doc.ents`, overlapping matches are allowed in `doc.spans`, so no
filtering is required, but optional filtering and sorting can be applied to the
spans before they're saved.
```python
### {executable="true"}
import spacy
nlp = spacy.blank("en")
ruler = nlp.add_pipe("span_ruler")
patterns = [{"label": "ORG", "pattern": "Apple"},
{"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}]
ruler.add_patterns(patterns)
doc = nlp("Apple is opening its first big office in San Francisco.")
print([(span.text, span.label_) for span in doc.spans["ruler"]])
```
The span ruler is designed to integrate with spaCy's existing pipeline
components and enhance the [SpanCategorizer](/api/spancat) and
[EntityRecognizer](/api/entityrecognizer). The `overwrite` setting determines
whether the existing annotation in `doc.spans` or `doc.ents` is preserved.
Because overlapping entities are not allowed for `doc.ents`, the entities are
always filtered, using [`util.filter_spans`](/api/top-level#util.filter_spans)
by default. See the [`SpanRuler` API docs](/api/spanruler) for more information
about how to customize the sorting and filtering of matched spans.
```python
### {executable="true"}
import spacy
nlp = spacy.load("en_core_web_sm")
# only annotate doc.ents, not doc.spans
config = {"spans_key": None, "annotate_ents": True, "overwrite": False}
ruler = nlp.add_pipe("span_ruler", config=config)
patterns = [{"label": "ORG", "pattern": "MyCorp Inc."}]
ruler.add_patterns(patterns)
doc = nlp("MyCorp Inc. is a company in the U.S.")
print([(ent.text, ent.label_) for ent in doc.ents])
```
### Using pattern files {#spanruler-files}
You can save patterns in a JSONL file (newline-delimited JSON) to load with
[`SpanRuler.initialize`](/api/spanruler#initialize) or
[`SpanRuler.add_patterns`](/api/spanruler#add_patterns).
```json
### patterns.jsonl
{"label": "ORG", "pattern": "Apple"}
{"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}
```
```python
import srsly
patterns = srsly.read_jsonl("patterns.jsonl")
ruler = nlp.add_pipe("span_ruler")
ruler.add_patterns(patterns)
```
<Infobox title="Important note" variant="warning">
Unlike the entity ruler, the span ruler cannot load patterns on initialization
with `SpanRuler(patterns=patterns)` or directly from a JSONL file path with
`SpanRuler.from_disk(jsonl_path)`. Patterns should be loaded from the JSONL file
separately and then added through
[`SpanRuler.initialize`](/api/spanruler#initialize]) or
[`SpanRuler.add_patterns`](/api/spanruler#add_patterns) as shown above.
</Infobox>
## Combining models and rules {#models-rules}
You can combine statistical and rule-based components in a variety of ways.

1
website/meta/sidebars.json
View File

@ -103,6 +103,7 @@
{ "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" },
{ "text": "Sentencizer", "url": "/api/sentencizer" },
{ "text": "SpanCategorizer", "url": "/api/spancategorizer" },
{ "text": "SpanRuler", "url": "/api/spanruler" },
{ "text": "Tagger", "url": "/api/tagger" },
{ "text": "TextCategorizer", "url": "/api/textcategorizer" },
{ "text": "Tok2Vec", "url": "/api/tok2vec" },