الاسترجاع والتجزئة ونطاق الوصول

import re
documents = [{"id": "refund-red", "tenant": "red", "text": "Refund window is 14 days."},
             {"id": "refund-blue", "tenant": "blue", "text": "Refund window is 90 days."},
             {"id": "shipping-red", "tenant": "red", "text": "Shipping takes two days."}]
query = {"refund", "window"}
allowed = [doc for doc in documents if doc["tenant"] == "red"]
scored = [(len(query & set(re.findall(r"[a-z]+", doc["text"].lower()))), doc["id"]) for doc in allowed]
print([doc_id for score, doc_id in sorted(scored, key=lambda row: (-row[0], row[1])) if score > 0])

['refund-red']

يعاد refund-red فقط بعد استبعاد الأزرق قبل الدرجة؛ وليس التعبير مرمزا متعدد اللغات أونموذجا.

def windows(words, width, overlap):
    if width <= 0 or overlap < 0 or overlap >= width:
        raise ValueError("invalid window")
    start = 0
    while start < len(words):
        yield " ".join(words[start:start + width])
        if start + width >= len(words):
            break
        start += width - overlap
print(list(windows("alpha beta gamma delta epsilon".split(), 3, 1)))

['alpha beta gamma', 'gamma delta epsilon']

تظهر gamma مرتين بتداخل بسيط دون ذيل مكرر ولا فهم جمل وحقائق ورموز.