"""统计 PDF 正文页的行距和每页行数，找页数偏差的来源。"""
import statistics, sys, pdfplumber
for path in sys.argv[1:]:
    pitches, counts, sizes, fonts = [], [], [], {}
    with pdfplumber.open(path) as pdf:
        for page in pdf.pages[5:25]:
            ys = sorted({round(c["top"], 1) for c in page.chars if c["text"].strip()})
            if len(ys) < 10:
                continue
            counts.append(len(ys))
            pitches += [b - a for a, b in zip(ys, ys[1:]) if 8 < b - a < 40]
            for c in page.chars:
                sizes.append(round(c["size"], 1)); fonts[c["fontname"].split("+")[-1]] = fonts.get(c["fontname"].split("+")[-1], 0) + 1
    print(path.split("/out/")[-1], "lines/page", statistics.median(counts), "pitch", statistics.median(pitches),
          "size", statistics.mode(sizes), sorted(fonts.items(), key=lambda x: -x[1])[:3])