Method add_patterns

spacy/pipeline/span_ruler.py:322–368

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'}, {

(self, patterns: List[PatternType])

        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.