exc_03_07.py

import spacy
from spacy.language import Language
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span

nlp = spacy.load("en_core_web_sm")
animals = ["Golden Retriever", "cat", "turtle", "Rattus norvegicus"]
animal_patterns = list(nlp.pipe(animals))
print("animal_patterns:", animal_patterns)
matcher = PhraseMatcher(nlp.vocab)
matcher.add("ANIMAL", animal_patterns)

# Define the custom component
@Language.component("animal_component")
def animal_component_function(doc):
    # Apply the matcher to the doc
    matches = ____
    # Create a Span for each match and assign the label "ANIMAL"
    spans = [Span(____, ____, ___, label=____) for match_id, start, end in matches]
    # Overwrite the doc.ents with the matched spans
    doc.ents = spans
    return doc


# Add the component to the pipeline after the "ner" component
____.____(____, ____=____)
print(nlp.pipe_names)

# Process the text and print the text and label for the doc.ents
doc = nlp("I have a cat and a Golden Retriever")
print([(____, ____) for ent in ____])