如何使用 Python 堆实现文本匹配模型？

import heapq

def string_match(keywords, text):
    # Convert keywords to priority queue form
    heap = [(-len(x), x, i) for i,x in enumerate(keywords)]
    heapq.heapify(heap)

    # Divide the text into equal length substrings
    size = -heap[0][0]
    substrings = [text[i:i+size] for i in range(0, len(text) - size + 1, size)]

    results = []

    # Insert substrings into heap
    for i,substring in enumerate(substrings):
        heapq.heappush(heap, (-len(substring), substring, i + len(keywords)))
        # Remove the old keyword from heap
        while heap[0][2] <= i:
            heapq.heappop(heap)
        # Compare the top of heap with substring
        if heap[0][1] == substring:
            results.append((i, heap[0][2] - len(keywords)))

    return results

# Sample usage
keywords = ['pidancode.com', '皮蛋编程']
text = 'pidancode.com is a website for learning programming, although 皮蛋编程 is also a good choice.'
results = string_match(keywords, text)
for start,end in results:
    print('Matched:', text[start:start+len(keywords[0])])