33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import re
|
||
|
|
|
||
|
|
|
||
|
|
def extract_match_terms(text: str | None) -> list[str]:
|
||
|
|
source = (text or "").lower()
|
||
|
|
terms = [token for token in re.findall(r"[a-z0-9_]+", source) if len(token) >= 3]
|
||
|
|
|
||
|
|
for chunk in re.findall(r"[\u4e00-\u9fff]+", text or ""):
|
||
|
|
if len(chunk) >= 2:
|
||
|
|
terms.append(chunk)
|
||
|
|
if len(chunk) > 4:
|
||
|
|
for index in range(len(chunk) - 1):
|
||
|
|
terms.append(chunk[index : index + 2])
|
||
|
|
|
||
|
|
return list(dict.fromkeys(terms))
|
||
|
|
|
||
|
|
|
||
|
|
def score_text_match(query_text: str, *corpus_parts: str | None) -> tuple[float, list[str]]:
|
||
|
|
query_terms = extract_match_terms(query_text)
|
||
|
|
if not query_terms:
|
||
|
|
return 0.0, []
|
||
|
|
|
||
|
|
corpus = " ".join(part for part in corpus_parts if part).lower()
|
||
|
|
matched_terms = [term for term in query_terms if term and term in corpus]
|
||
|
|
if not matched_terms:
|
||
|
|
return 0.0, []
|
||
|
|
|
||
|
|
coverage = len(matched_terms) / max(len(query_terms), 1)
|
||
|
|
density = min(len(matched_terms), 4) / 4
|
||
|
|
return round(min(1.0, coverage * 0.7 + density * 0.3), 3), matched_terms
|