feat: add context_getter argument to eds.matcher

changelog.md

@@ -11,6 +11,7 @@
 - `edsnlp.load` now accepts EDS-NLP models from the huggingface hub 🤗 !
 - New `python -m edsnlp.package` command to package a model for the huggingface hub or pypi-like registries
 - Expose the defaults patterns of `eds.negation`, `eds.hypothesis`, `eds.family`, `eds.history` and `eds.reported_speech` under a `eds.negation.default_patterns` attribute
+- Added a `context_getter` SpanGetter argument to the `eds.matcher` class to only retrieve entities inside the spans returned by the getter
 
 ### Changed
 

edsnlp/pipes/core/matcher/matcher.py

@@ -9,6 +9,7 @@
 from edsnlp.matchers.simstring import SimstringMatcher
 from edsnlp.matchers.utils import Patterns
 from edsnlp.pipes.base import BaseNERComponent, SpanSetterArg
+from edsnlp.utils.span_getters import SpanGetterArg, get_spans
 
 
 class GenericMatcher(BaseNERComponent):
@@ -102,6 +103,7 @@ def __init__(
         term_matcher: Literal["exact", "simstring"] = "exact",
         term_matcher_config: Dict[str, Any] = {},
         span_setter: SpanSetterArg = {"ents": True},
+        context_getter: Optional[SpanGetterArg] = None,
     ):
         super().__init__(nlp=nlp, name=name, span_setter=span_setter)
 
@@ -114,6 +116,7 @@ def __init__(
         regex = regex or {}
 
         self.attr = attr
+        self.context_getter = context_getter
 
         if term_matcher == "exact":
             self.phrase_matcher = EDSPhraseMatcher(
@@ -163,10 +166,16 @@ def process(self, doc: Doc) -> List[Span]:
             List of Spans returned by the matchers.
         """
 
-        matches = self.phrase_matcher(doc, as_spans=True)
-        regex_matches = self.regex_matcher(doc, as_spans=True)
-
-        spans = list(matches) + list(regex_matches)
+        contexts = (
+            list(get_spans(doc, self.context_getter))
+            if self.context_getter is not None
+            else [doc]
+        )
+        spans: List[Span] = []
+        for context in contexts:
+            matches = self.phrase_matcher(context, as_spans=True)
+            regex_matches = self.regex_matcher(context, as_spans=True)
+            spans.extend(list(matches) + list(regex_matches))
 
         return spans