feat: in eds.dates new option for shared date label and assign durati…

…on to separate span group

changelog.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## Unreleased
+
+### Added
+
+- New `to_duration` method to convert an absolute date into a date relative to the note_datetime (or None)
+- New `use_date_label` in `eds.dates` to store absolute and relative dates under a same `date` label (instead of `absolute` and `relative`)
+
+### Changed
+
+- Duration time entities (from `eds.dates`) are now stored in the `durations` span group, different than the `dates` span group
+- `to_datetime` now only return absolute dates, converts relative dates into absolute if `doc._.note_datetime` is given, and None otherwise
+
 ## v0.8.0 (2023-03-09)
 
 ### Added

edsnlp/pipelines/misc/dates/dates.py

@@ -55,6 +55,9 @@ class Dates(BaseComponent):
         Whether to treat dates as entities
     attr : str
         spaCy attribute to use
+    use_date_label: bool
+        Whether to use a shared `date` label for absolute and relative dates
+        instead of `absolute` and `relative` labels
     """
 
     # noinspection PyProtectedMember
@@ -70,8 +73,10 @@ def __init__(
         detect_time: bool,
         as_ents: bool,
         attr: str,
+        use_date_label: bool = False,
     ):
 
+        self.use_date_label = use_date_label
         self.nlp = nlp
 
         if absolute is None:
@@ -195,8 +200,12 @@ def parse(self, dates: List[Tuple[Span, Dict[str, str]]]) -> List[Span]:
         for span, groupdict in dates:
             if span.label_ == "relative":
                 parsed = RelativeDate.parse_obj(groupdict)
+                if self.use_date_label:
+                    span.label_ = "date"
             elif span.label_ == "absolute":
                 parsed = AbsoluteDate.parse_obj(groupdict)
+                if self.use_date_label:
+                    span.label_ = "date"
             else:
                 parsed = Duration.parse_obj(groupdict)
 
@@ -277,7 +286,8 @@ def __call__(self, doc: Doc) -> Doc:
         dates = self.process(doc)
         dates = self.parse(dates)
 
-        doc.spans["dates"] = dates
+        doc.spans["dates"] = [d for d in dates if d.label_ != "duration"]
+        doc.spans["durations"] = [d for d in dates if d.label_ == "duration"]
 
         if self.detect_periods:
             doc.spans["periods"] = self.process_periods(dates)

edsnlp/pipelines/misc/dates/factory.py

@@ -35,6 +35,7 @@ def create_component(
     detect_time: bool = True,
     as_ents: bool = False,
     attr: str = "LOWER",
+    use_date_label: bool = False,
 ):
     """
     Tags and normalizes dates, using the open-source `dateparser` library.
@@ -73,6 +74,9 @@ def create_component(
         Whether to treat dates as entities
     attr : str
         spaCy attribute to use
+    use_date_label: bool
+        Whether to use a shared `date` label for absolute and relative dates
+        instead of `absolute` and `relative` labels
     """
     return Dates(
         nlp,
@@ -85,4 +89,5 @@ def create_component(
         detect_time=detect_time,
         as_ents=as_ents,
         attr=attr,
+        use_date_label=use_date_label,
     )

tests/pipelines/misc/test_dates.py

@@ -84,10 +84,12 @@ def test_dates_component(blank_nlp: Language):
 
         doc = blank_nlp(text)
 
-        assert len(doc.spans["dates"]) == len(entities)
+        assert len((*doc.spans["dates"], *doc.spans["durations"])) == len(entities)
         assert len(doc.ents) == len(entities)
 
-        for span, entity in zip(doc.spans["dates"], entities):
+        for span, entity in zip(
+            (*doc.spans["dates"], *doc.spans["durations"]), entities
+        ):
             assert span.text == text[entity.start_char : entity.end_char]
 
             date = span._.date
@@ -227,9 +229,11 @@ def test_time(with_time: bool):
 
         doc = nlp(text)
 
-        assert len(doc.spans["dates"]) == len(entities)
+        assert len((*doc.spans["dates"], *doc.spans["durations"])) == len(entities)
 
-        for span, entity in zip(doc.spans["dates"], entities):
+        for span, entity in zip(
+            (*doc.spans["dates"], *doc.spans["durations"]), entities
+        ):
             assert span.text == text[entity.start_char : entity.end_char]
             norm = next(m.value for m in entity.modifiers if m.key == "norm")
             assert span._.date.norm() == norm
@@ -257,7 +261,7 @@ def test_false_positives(blank_nlp: Language):
     for example in counter_examples:
         doc = blank_nlp(example)
 
-        assert len(doc.spans["dates"]) == 0
+        assert len((*doc.spans["dates"], *doc.spans["durations"])) == 0
 
 
 def test_dates_on_ents_only():
@@ -280,9 +284,9 @@ def test_dates_on_ents_only():
 
     assert len(doc.ents) == 1
 
-    assert len(doc.spans["dates"]) == len(entities)
+    assert len((*doc.spans["dates"], *doc.spans["durations"])) == len(entities)
 
-    for span, entity in zip(doc.spans["dates"], entities):
+    for span, entity in zip((*doc.spans["dates"], *doc.spans["durations"]), entities):
         assert span.text == text[entity.start_char : entity.end_char]
 
 
@@ -293,5 +297,11 @@ def test_illegal_dates(blank_nlp):
     )
     for text in texts:
         doc = blank_nlp(text)
-        ent = doc.spans["dates"][0]
+        ent = (*doc.spans["dates"], *doc.spans["durations"])[0]
         assert ent._.date.to_datetime() is None
+
+
+def test_date_label():
+    nlp = spacy.blank("eds")
+    nlp.add_pipe("eds.dates", config={"use_date_label": True, "as_ents": True})
+    assert nlp("Le 31/06/17, la dernière dose.").ents[0].label_ == "date"