Remove pollution exclusion during numbers matching

[percevalw]

Description

Fixes #315
Error was caused by a pollution spans being between two numbers. We obviously don't want to match numbers that are not contiguous spans of text, even under the assumption that the text extraction was faulty so I disabled the ignore_pollution of the number regex matcher.

Checklist

• If this PR is a bug fix, the bug is documented in the test suite.
• Changes were documented in the changelog (pending section).
• If necessary, changes were made to the documentation (eg new pipeline).

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarCloud

[github-actions]

Coverage Report

Name	Stmts	Miss	∆ Miss	Cover
TOTAL	9313	209	0	97.76%

Files without new missing coverage

Name	Stmts	Miss	∆ Miss	Cover
edsnlp/utils/span_getters.py Was already missing at lines 52-55 else: - for span in candidates: - if span.label_ in span_filter: - yield span Was already missing at lines 59-61 if span_getter is None: - yield doc[:], None - return if callable(span_getter): Was already missing at lines 62-64 if callable(span_getter): - yield from span_getter(doc) - return for key, span_filter in span_getter.items(): Was already missing at line 66 if key == "*": - candidates = ( (span, group) for group in doc.spans.values() for span in group Was already missing at lines 75-78 else: - for span, group in candidates: - if span.label_ in span_filter: - yield span, group Was already missing at line 82 if callable(span_setter): - span_setter(doc, matches) else: Was already missing at line 124 elif isinstance(v, str): - new_value[k] = [v] elif isinstance(v, list) and all(isinstance(i, str) for i in v): Was already missing at line 162 elif isinstance(v, str): - new_value[k] = [v] elif isinstance(v, list) and all(isinstance(i, str) for i in v):	153	14	0	90.85%
edsnlp/utils/resources.py Was already missing at line 33 if not verbs: - return conjugated_verbs	24	1	0	95.83%
edsnlp/utils/numbers.py Was already missing at line 34 else: - string = s string = string.lower().strip() Was already missing at lines 38-41 return int(string) - except ValueError: - parsed = DIGITS_MAPPINGS.get(string, None) - return parsed	16	4	0	75.00%
edsnlp/utils/lazy_module.py Was already missing at line 46 ): - continue for import_node in node.body:	31	1	0	96.77%
edsnlp/utils/filter.py Was already missing at line 206 if isinstance(label, int): - return [span for span in spans if span.label == label] else:	74	1	0	98.65%
edsnlp/utils/bindings.py Was already missing at line 22 return "." + path - return path	66	1	0	98.48%
edsnlp/train.py Was already missing at line 190 else: - sample_len = lambda idx, noise=True: 1 # noqa: E731 Was already missing at lines 257-263 if total + num_tokens > self.grad_accumulation_max_tokens: - print( ... - mini_batches.append([]) total += num_tokens Was already missing at line 349 if 0 <= self.limit <= count: - break if not (len(doc) and (filter_fn is None or filter_fn(doc))): Was already missing at line 351 if not (len(doc) and (filter_fn is None or filter_fn(doc))): - continue count += 1 Was already missing at lines 385-387 for ent in doc.ents: - for token in ent: - token.is_sent_start = False for sent in doc.sents if doc.has_annotation("SENT_START") else (doc[:],):	257	8	0	96.89%
edsnlp/processing/spark.py Was already missing at line 51 getActiveSession = SparkSession.getActiveSession - except AttributeError:	43	1	0	97.67%
edsnlp/processing/multiprocessing.py Was already missing at lines 227-231 if os.environ.get("TORCH_SHARING_STRATEGY"): - try: - torch.multiprocessing.set_sharing_strategy(os.environ["TORCH_SHARING_STRATEGY"]) - except NameError: - pass Was already missing at line 249 def save_align_devices_hook(pickler: Any, obj: Any): - pickler.save_reduce(load_align_devices_hook, (obj.__dict__,), obj=obj) Was already missing at lines 252-259 def load_align_devices_hook(state): - state["execution_device"] = MAP_LOCATION ... - AlignDevicesHook = None Was already missing at line 452 - new_batch_iterator = None Was already missing at lines 570-572 else: - batch = gpu_pipe.prepare_batch(docs, device=device) - inputs = None active_batches[batch_id] = (docs, task_id, inputs) Was already missing at line 949 if isinstance(outputs, BaseException): - raise outputs Was already missing at line 1017 if v is not None: - os.environ[k] = v	420	16	0	96.19%
edsnlp/processing/deprecated_pipe.py Was already missing at lines 207-209 def converter(doc): - res = results_extractor(doc) - return ( [{"note_id": doc._.note_id, **row} for row in res]	57	2	0	96.49%
edsnlp/pipes/trainable/span_linker/span_linker.py Was already missing at lines 401-403 if self.reference_mode == "synonym": - embeds = embeds.to(new_lin.weight) - new_lin.weight.data = embeds else:	172	2	0	98.84%
edsnlp/pipes/trainable/ner_crf/ner_crf.py Was already missing at line 250 if self.labels is not None and not self.infer_span_setter: - return Was already missing at lines 258-260 if callable(self.target_span_getter): - for span in get_spans(doc, self.target_span_getter): - inferred_labels.add(span.label_) else:	157	3	0	98.09%
edsnlp/pipes/trainable/layers/crf.py Was already missing at line 21 # out: 2 * N * O - return (log_A.unsqueeze(-1) + log_B.unsqueeze(-3)).logsumexp(-2) Was already missing at line 29 # out: 2 * N * O - return (log_A.unsqueeze(-1) + log_B.unsqueeze(-3)).max(-2) Was already missing at line 97 if learnable_transitions: - self.transitions = torch.nn.Parameter( torch.zeros_like(forbidden_transitions, dtype=torch.float) Was already missing at line 107 if learnable_transitions and with_start_end_transitions: - self.start_transitions = torch.nn.Parameter( torch.zeros(num_tags, dtype=torch.float) Was already missing at line 116 if learnable_transitions and with_start_end_transitions: - self.end_transitions = torch.nn.Parameter( torch.zeros(num_tags, dtype=torch.float)	137	5	0	96.35%
edsnlp/pipes/trainable/embeddings/transformer/transformer.py Was already missing at line 165 if quantization is not None: - kwargs["quantization_config"] = quantization	157	1	0	99.36%
edsnlp/pipes/qualifiers/reported_speech/reported_speech.py Was already missing at lines 18-22 return "REPORTED" - elif token._.rspeech is False: - return "DIRECT" - else: - return None	73	3	0	95.89%
edsnlp/pipes/qualifiers/negation/negation.py Was already missing at line 22 else: - return None	77	1	0	98.70%
edsnlp/pipes/qualifiers/hypothesis/hypothesis.py Was already missing at line 21 else: - return None	74	1	0	98.65%
edsnlp/pipes/qualifiers/history/history.py Was already missing at lines 20-26 def history_getter(token: Union[Token, Span]) -> Optional[str]: - if token._.history is True: - return "ATCD" - elif token._.history is False: - return "CURRENT" - else: - return None Was already missing at lines 310-316 ) - except ValueError: ... - note_datetime = None Was already missing at lines 325-331 ) - except ValueError: ... - birth_datetime = None Was already missing at lines 397-400 ) - except ValueError as e: - absolute_date = None - logger.warning( "In doc {}, the following date {} raises this error: {}. "	154	14	0	90.91%
edsnlp/pipes/qualifiers/family/family.py Was already missing at line 21 else: - return None	59	1	0	98.31%
edsnlp/pipes/ner/tnm/tnm.py Was already missing at lines 156-158 value = TNM.parse_obj(groupdict) - except ValidationError: - value = TNM.parse_obj({})	44	2	0	95.45%
edsnlp/pipes/ner/tnm/model.py Was already missing at line 139 def __str__(self): - return self.norm() Was already missing at line 163 ) - exclude_unset = skip_defaults	104	2	0	98.08%
edsnlp/pipes/ner/scores/sofa/sofa.py Was already missing at line 32 if not assigned: - continue if assigned.get("method_max") is not None: Was already missing at line 40 else: - method = "Non précisée"	25	2	0	92.00%
edsnlp/pipes/ner/scores/elston_ellis/patterns.py Was already missing at line 26 if x <= 5: - return 1 Was already missing at lines 32-36 else: - return 3 - - except ValueError: - return None	21	4	0	80.95%
edsnlp/pipes/ner/scores/charlson/patterns.py Was already missing at lines 21-23 return int(extracted_score) - except ValueError: - return None	13	2	0	84.62%
edsnlp/pipes/ner/scores/base_score.py Was already missing at line 154 if value is None: - continue normalized_value = self.score_normalization(value)	47	1	0	97.87%
edsnlp/pipes/ner/disorders/solid_tumor/solid_tumor.py Was already missing at lines 114-117 if use_tnm: - from edsnlp.pipes.ner.tnm import TNM - - self.tnm = TNM(nlp, pattern=None, attr="TEXT") Was already missing at lines 119-129 def process_tnm(self, doc): - spans = self.tnm.process(doc) ... - yield span Was already missing at line 149 if self.use_tnm: - yield from self.process_tnm(doc)	35	12	0	65.71%
edsnlp/pipes/ner/disorders/peripheral_vascular_disease/peripheral_vascular_disease.py Was already missing at line 106 if "peripheral" not in span._.assigned.keys(): - continue	15	1	0	93.33%
edsnlp/pipes/ner/disorders/diabetes/diabetes.py Was already missing at line 133 # Mostly FP - continue Was already missing at line 136 elif self.has_far_complications(span): - span._.status = 2 Was already missing at line 148 if next(iter(self.complication_matcher(context)), None) is not None: - return True return False	31	3	0	90.32%
edsnlp/pipes/ner/disorders/connective_tissue_disease/connective_tissue_disease.py Was already missing at line 102 # Huge change of FP / Title section - continue	14	1	0	92.86%
edsnlp/pipes/ner/disorders/ckd/ckd.py Was already missing at lines 119-122 dfg_value = float(dfg_span.text.replace(",", ".").strip()) - except ValueError: - logger.trace(f"DFG value couldn't be extracted from {dfg_span.text}") - return False	29	3	0	89.66%
edsnlp/pipes/ner/disorders/cerebrovascular_accident/cerebrovascular_accident.py Was already missing at lines 110-112 if span._.source == "ischemia": - if "brain" not in span._.assigned.keys(): - continue	17	2	0	88.24%
edsnlp/pipes/ner/adicap/models.py Was already missing at line 15 def norm(self) -> str: - return self.code Was already missing at line 18 def __str__(self): - return self.norm()	14	2	0	85.71%
edsnlp/pipes/misc/sections/sections.py Was already missing at line 126 if sections is None: - sections = patterns.sections sections = dict(sections)	45	1	0	97.78%
edsnlp/pipes/misc/measurements/measurements.py Was already missing at lines 147-149 def __getitem__(self, item: int): - assert isinstance(item, int) - return [self][item] Was already missing at lines 160-163 def __eq__(self, other: Any): - if isinstance(other, SimpleMeasurement): - return self.convert_to(other.unit) == other.value - return False Was already missing at line 166 if other.unit == self.unit: - return self.__class__(self.value + other.value, self.unit, self.registry) return self.__class__( Was already missing at line 193 return self.convert_to(other_unit) - except KeyError: raise AttributeError(f"Unit {other_unit} not found") Was already missing at line 198 def verify(cls, ent): - return True Was already missing at line 237 def __lt__(self, other: Union[SimpleMeasurement, "RangeMeasurement"]): - return max(self.convert_to(other.unit)) < min((part.value for part in other)) Was already missing at line 248 return self.convert_to(other.unit) == other.value - return False Was already missing at line 262 def verify(cls, ent): - return True Was already missing at line 857 if snippet.end != last and doclike.doc[last: snippet.end].text.strip() == "": - pseudo.append("w") pseudo = "".join(pseudo) Was already missing at line 1031 if start_line is None: - continue Was already missing at lines 1062-1064 unit_norm = self.unit_followers[unit_before.label_] - except (KeyError, AttributeError, IndexError): - pass Was already missing at line 1107 ): - ent = doc[unit_text.start: number.end] else: Was already missing at lines 1114-1116 dims = self.unit_registry.parse_unit(unit_norm)[0] - except KeyError: - continue Was already missing at lines 1227-1229 last._.set(last.label_, new_value) - except (AttributeError, TypeError): - merged.append(ent) else:	429	20	0	95.34%
edsnlp/pipes/misc/dates/models.py Was already missing at line 152 else: - d["month"] = note_datetime.month if self.day is None: Was already missing at lines 156-162 else: - if self.year is None: ... - d["day"] = default_day Was already missing at lines 170-172 return dt - except ValueError: - return None Was already missing at line 188 else: - return None Was already missing at line 204 if self.second: - norm += f"{self.second:02}s"	196	11	0	94.39%
edsnlp/pipes/misc/dates/dates.py Was already missing at line 248 if isinstance(absolute, str): - absolute = [absolute] if isinstance(relative, str): Was already missing at line 250 if isinstance(relative, str): - relative = [relative] if isinstance(duration, str): Was already missing at line 252 if isinstance(duration, str): - relative = [duration] if isinstance(false_positive, str): Was already missing at lines 356-365 if self.merge_mode == "align": - alignments = align_spans(matches, spans, sort_by_overlap=True) ... - matches.append(span) Was already missing at line 450 elif d1 in seen or v1.bound is None or v2.bound is None: - continue Was already missing at lines 461-463 if v1.mode == Mode.DURATION: - m1 = Bound.FROM if v2.bound == Bound.UNTIL else Bound.UNTIL - m2 = v2.mode or Bound.FROM elif v2.mode == Mode.DURATION:	152	15	0	90.13%
edsnlp/pipes/misc/consultation_dates/consultation_dates.py Was already missing at line 131 else: - self.date_matcher = None Was already missing at line 134 if not consultation_mention: - consultation_mention = [] elif consultation_mention is True:	48	2	0	95.83%
edsnlp/pipes/core/normalizer/__init__.py Was already missing at line 7 def excluded_or_space_getter(t): - return t.is_space or t.tag_ == "EXCLUDED"	5	1	0	80.00%
edsnlp/pipes/core/endlines/endlines.py Was already missing at lines 151-155 if end_lines_model is None: - path = build_path(__file__, "base_model.pkl") - - with open(path, "rb") as inp: - self.model = pickle.load(inp) elif isinstance(end_lines_model, str): Was already missing at lines 158-160 self.model = pickle.load(inp) - elif isinstance(end_lines_model, EndLinesModel): - self.model = end_lines_model else: Was already missing at line 191 ): - return "ENUMERATION" Was already missing at line 278 if np.isnan(sigma): - sigma = 1	87	7	0	91.95%
edsnlp/pipes/core/contextual_matcher/models.py Was already missing at lines 19-23 if isinstance(v, list): - assert ( - len(v) == 2 - ), "`window` should be a tuple/list of two integer, or a single integer" - v = tuple(v) if isinstance(v, int):	115	2	0	98.26%
edsnlp/pipes/core/contextual_matcher/contextual_matcher.py Was already missing at line 94 ) - label = label_name if label is None: Was already missing at line 343 if assigned is None: - continue if replace_entity:	143	2	0	98.60%
edsnlp/patch_spacy.py Was already missing at lines 67-69 # if module is reloaded. - existing_func = registry.factories.get(internal_name) - if not util.is_same_func(factory_func, existing_func): raise ValueError(	31	2	0	93.55%
edsnlp/optimization.py Was already missing at line 32 def param_groups(self, value): - self.optim.param_groups = value Was already missing at line 36 def state(self): - return self.optim.state Was already missing at line 40 def state(self, value): - self.optim.state = value Was already missing at line 89 def __init__(self, groups): - self.param_groups = groups	77	4	0	94.81%
edsnlp/matchers/simstring.py Was already missing at line 280 if custom: - attr = attr[1:].lower() Was already missing at line 295 if custom: - token_text = getattr(token._, attr) else:	146	2	0	98.63%
edsnlp/language.py Was already missing at line 103 if last != begin: - logger.warning( "Missed some characters during"	51	1	0	98.04%
edsnlp/data/standoff.py Was already missing at line 43 def __init__(self, ann_file, line): - super().__init__(f"File {ann_file}, unrecognized Brat line {line}") Was already missing at line 83 if not len(ann_paths): - return { "text": text, Was already missing at line 197 ) - except Exception: raise Exception(	172	3	0	98.26%
edsnlp/data/polars.py Was already missing at line 26 if hasattr(data, "collect"): - data = data.collect() assert isinstance(data, pl.DataFrame)	44	1	0	97.73%
edsnlp/data/json.py Was already missing at line 94 if not is_jsonl: - obj[FILENAME] = filename results.append(obj) Was already missing at line 96 results.append(obj) - except Exception: raise Exception(f"Cannot parse {filename}")	107	2	0	98.13%
edsnlp/data/converters.py Was already missing at line 659 if isinstance(converter, type) or kwargs_to_init: - return converter(**kwargs), {} return converter, validate_kwargs(converter, kwargs)	192	1	0	99.48%
edsnlp/data/base.py Was already missing at lines 174-180 """ - data = LazyCollection.ensure_lazy(data) - if converter: - converter, kwargs = get_doc2dict_converter(converter, kwargs) - data = data.map(converter, kwargs=kwargs) - - return data	39	5	0	87.18%
edsnlp/core/torch_component.py Was already missing at line 390 if hasattr(self, "compiled"): - res = self.compiled(batch) else: Was already missing at line 436 """ - return self.preprocess(doc)	179	2	0	98.88%
edsnlp/core/registries.py Was already missing at line 78 if obj.error is not None: - raise obj.error	164	1	0	99.39%
edsnlp/core/pipeline.py Was already missing at line 552 if name in exclude: - continue if name not in components:	410	1	0	99.76%
edsnlp/core/lazy_collection.py Was already missing at line 51 def __call__(self, *args, **kwargs): - return self.forward(*args, **kwargs) Was already missing at line 448 for name, pipe, *_ in self.torch_components(): - pipe.to(device) return self	151	2	0	98.68%
edsnlp/connectors/omop.py Was already missing at line 69 if not isinstance(row.ents, list): - continue Was already missing at line 87 else: - doc.spans[span.label_].append(span) Was already missing at line 127 if df.note_id.isna().any(): - df["note_id"] = range(len(df)) Was already missing at line 171 if i > 0: - df.term_modifiers += ";" df.term_modifiers += ext + "=" + df[ext].astype(str)	84	4	0	95.24%

264 files skipped due to complete coverage.

Coverage success: total of 97.76% is above 97.75% 🎉