mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 05:07:03 +03:00
19650ebb52
* enable fuzzy matching * add fuzzy param to EntityMatcher * include rapidfuzz_capi not yet used * fix type * add FUZZY predicate * add fuzzy attribute list * fix type properly * tidying * remove unnecessary dependency * handle fuzzy sets * simplify fuzzy sets * case fix * switch to FUZZYn predicates use Levenshtein distance. remove fuzzy param. remove rapidfuzz_capi. * revert changes added for fuzzy param * switch to polyleven (Python package) * enable fuzzy matching * add fuzzy param to EntityMatcher * include rapidfuzz_capi not yet used * fix type * add FUZZY predicate * add fuzzy attribute list * fix type properly * tidying * remove unnecessary dependency * handle fuzzy sets * simplify fuzzy sets * case fix * switch to FUZZYn predicates use Levenshtein distance. remove fuzzy param. remove rapidfuzz_capi. * revert changes added for fuzzy param * switch to polyleven (Python package) * fuzzy match only on oov tokens * remove polyleven * exclude whitespace tokens * don't allow more edits than characters * fix min distance * reinstate FUZZY operator with length-based distance function * handle sets inside regex operator * remove is_oov check * attempt build fix no mypy failure locally * re-attempt build fix * don't overwrite fuzzy param value * move fuzzy_match to its own Python module to allow patching * move fuzzy_match back inside Matcher simplify logic and add tests * Format tests * Parametrize fuzzyn tests * Parametrize and merge fuzzy+set tests * Format * Move fuzzy_match to a standalone method * Change regex kwarg type to bool * Add types for fuzzy_match - Refactor variable names - Add test for symmetrical behavior * Parametrize fuzzyn+set tests * Minor refactoring for fuzz/fuzzy * Make fuzzy_match a Matcher kwarg * Update type for _default_fuzzy_match * don't overwrite function param * Rename to fuzzy_compare * Update fuzzy_compare default argument declarations * allow fuzzy_compare override from EntityRuler * define new Matcher keyword arg * fix type definition * Implement fuzzy_compare config option for EntityRuler and SpanRuler * Rename _default_fuzzy_compare to fuzzy_compare, remove from reexported objects * Use simpler fuzzy_compare algorithm * Update types * Increase minimum to 2 in fuzzy_compare to allow one transposition * Fix predicate keys and matching for SetPredicate with FUZZY and REGEX * Add FUZZY6..9 * Add initial docs * Increase default fuzzy to rounded 30% of pattern length * Update docs for fuzzy_compare in components * Update EntityRuler and SpanRuler API docs * Rename EntityRuler and SpanRuler setting to matcher_fuzzy_compare To having naming similar to `phrase_matcher_attr`, rename `fuzzy_compare` setting for `EntityRuler` and `SpanRuler` to `matcher_fuzzy_compare. Organize next to `phrase_matcher_attr` in docs. * Fix schema aliases Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix typo Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add FUZZY6-9 operators and update tests * Parameterize test over greedy Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix type for fuzzy_compare to remove Optional * Rename to spacy.levenshtein_compare.v1, move to spacy.matcher.levenshtein * Update docs following levenshtein_compare renaming Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
from typing import Any, List, Dict, Tuple, Optional, Callable, Union
|
|
from typing import Iterator, Iterable, overload
|
|
from ..compat import Literal
|
|
from ..vocab import Vocab
|
|
from ..tokens import Doc, Span
|
|
|
|
class Matcher:
|
|
def __init__(self, vocab: Vocab, validate: bool = ...,
|
|
fuzzy_compare: Callable[[str, str, int], bool] = ...) -> None: ...
|
|
def __reduce__(self) -> Any: ...
|
|
def __len__(self) -> int: ...
|
|
def __contains__(self, key: str) -> bool: ...
|
|
def add(
|
|
self,
|
|
key: Union[str, int],
|
|
patterns: List[List[Dict[str, Any]]],
|
|
*,
|
|
on_match: Optional[
|
|
Callable[[Matcher, Doc, int, List[Tuple[Any, ...]]], Any]
|
|
] = ...,
|
|
greedy: Optional[str] = ...
|
|
) -> None: ...
|
|
def remove(self, key: str) -> None: ...
|
|
def has_key(self, key: Union[str, int]) -> bool: ...
|
|
def get(
|
|
self, key: Union[str, int], default: Optional[Any] = ...
|
|
) -> Tuple[Optional[Callable[[Any], Any]], List[List[Dict[Any, Any]]]]: ...
|
|
def pipe(
|
|
self,
|
|
docs: Iterable[Tuple[Doc, Any]],
|
|
batch_size: int = ...,
|
|
return_matches: bool = ...,
|
|
as_tuples: bool = ...,
|
|
) -> Union[
|
|
Iterator[Tuple[Tuple[Doc, Any], Any]], Iterator[Tuple[Doc, Any]], Iterator[Doc]
|
|
]: ...
|
|
@overload
|
|
def __call__(
|
|
self,
|
|
doclike: Union[Doc, Span],
|
|
*,
|
|
as_spans: Literal[False] = ...,
|
|
allow_missing: bool = ...,
|
|
with_alignments: bool = ...
|
|
) -> List[Tuple[int, int, int]]: ...
|
|
@overload
|
|
def __call__(
|
|
self,
|
|
doclike: Union[Doc, Span],
|
|
*,
|
|
as_spans: Literal[True],
|
|
allow_missing: bool = ...,
|
|
with_alignments: bool = ...
|
|
) -> List[Span]: ...
|
|
def _normalize_key(self, key: Any) -> Any: ...
|