solution_03_12.py

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

with open("exercises/en/countries.json", encoding="utf8") as f:
    COUNTRIES = json.loads(f.read())

with open("exercises/en/capitals.json", encoding="utf8") as f:
    CAPITALS = json.loads(f.read())

nlp = spacy.blank("en")
matcher = PhraseMatcher(nlp.vocab)
matcher.add("COUNTRY", list(nlp.pipe(COUNTRIES)))


@Language.component("countries_component")
def countries_component_function(doc):
    # Create an entity Span with the label "GPE" for all matches
    matches = matcher(doc)
    doc.ents = [Span(doc, start, end, label="GPE") for match_id, start, end in matches]
    return doc


# Add the component to the pipeline
nlp.add_pipe("countries_component")
print(nlp.pipe_names)

# Getter that looks up the span text in the dictionary of country capitals
get_capital = lambda span: CAPITALS.get(span.text)

# Register the Span extension attribute "capital" with the getter get_capital
Span.set_extension("capital", getter=get_capital)

# Process the text and print the entity text, label and capital attributes
doc = nlp("Czech Republic may help Slovakia protect its airspace")
print([(ent.text, ent.label_, ent._.capital) for ent in doc.ents])