refactor(ebook): remove spaCy-ner attributes from PhraseCandidate and related functions

This commit is contained in:
2026-07-16 13:09:34 -04:00
parent ef9ad1a6d6
commit 5bff9e82fc
5 changed files with 58 additions and 121 deletions
@@ -295,11 +295,8 @@ def phrase_candidate_from_row(row: EbookCandidatePhrase) -> PhraseCandidate:
token_count=row.token_count,
source_raw_ngram=row.source_raw_ngram,
source_yake=row.source_yake,
source_spacy_ner=row.source_spacy_ner,
source_spacy_noun_chunk=row.source_spacy_noun_chunk,
source_capitalized=row.source_capitalized,
source_metadata=row.source_metadata,
spacy_label=row.spacy_label,
raw_count=row.raw_count,
chapter_count=row.chapter_count,
yake_score=row.yake_score,
@@ -334,11 +331,8 @@ def candidate_row_values(
"token_count": candidate.token_count,
"source_raw_ngram": candidate.source_raw_ngram,
"source_yake": candidate.source_yake,
"source_spacy_ner": candidate.source_spacy_ner,
"source_spacy_noun_chunk": candidate.source_spacy_noun_chunk,
"source_capitalized": candidate.source_capitalized,
"source_metadata": candidate.source_metadata,
"spacy_label": candidate.spacy_label,
"raw_count": candidate.raw_count,
"chapter_count": candidate.chapter_count,
"yake_score": candidate.yake_score,
@@ -460,11 +454,8 @@ def new_candidate_row(book_id: int, series_id: int | None, candidate: PhraseCand
row.token_count = candidate.token_count
row.source_raw_ngram = candidate.source_raw_ngram
row.source_yake = candidate.source_yake
row.source_spacy_ner = candidate.source_spacy_ner
row.source_spacy_noun_chunk = candidate.source_spacy_noun_chunk
row.source_capitalized = candidate.source_capitalized
row.source_metadata = candidate.source_metadata
row.spacy_label = candidate.spacy_label
row.raw_count = candidate.raw_count
row.chapter_count = candidate.chapter_count
row.yake_score = candidate.yake_score