import json

with open('peiwenyunfu.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

mismatches = []
prefixes_found = set()

for rhyme, r_data in data.items():
    if rhyme in ["metadata", "preface"]:
        continue
    for word, content in r_data.get("词条", {}).items():
        pipe_count = content.count("丨")
        if pipe_count == 0:
            continue
        if pipe_count % len(word) != 0:
            mismatches.append((word, pipe_count))

print(f"Total mismatches: {len(mismatches)}")
for w, p in mismatches[:20]:
    print(f"{w} (len {len(w)}), pipes: {p}")