重构 document-photo-to-pdf:审核页改为 data.db 驱动并支持一键重生成
run.py 接上 edits/enhance/dpi/status/review,并把运行记录写进会话 data.db;审核页模板移到 skill/web,运行时发布到 .app/doc-review/,页面通过 /api/db 水合并调用通用技能执行接口重生成;移除 make_review.py 与模板注入。
This commit is contained in:
@@ -1,20 +1,11 @@
|
||||
"""PDF 产出的通用质量检验(渲染真实页面后评估)。
|
||||
# -*- coding: utf-8 -*-
|
||||
"""PDF 产出的数值检验:渲染真实页面后评估,不画图、不修改文件。
|
||||
|
||||
检验对象是最终交付的 PDF,不是中间图:把每页按固定 DPI 渲染成位图,
|
||||
在渲染结果上做统计判定,所见即交付物。
|
||||
|
||||
检验项:
|
||||
1. 页数与源图数一致
|
||||
2. 有效内容分辨率(页面渲染后纸面区域的像素尺寸)
|
||||
3. 纸张比例失真(纸面外接框的宽高比,对照页面书写比例)
|
||||
4. 纸面外背景残留(边带亮度显著低于纸面)
|
||||
5. 内容贴边被切(页边存在成片文字级暗像素)
|
||||
|
||||
判据全部基于该页自身像素分布自适应(Otsu / 分位数),不含针对特定文档的常量。
|
||||
|
||||
用法:
|
||||
python3 doc_deskew/check.py 结果.pdf [--expect-pages 2] [--dpi 100]
|
||||
python3 doc_deskew/check.py 结果.pdf --render # 导出渲染图供目视
|
||||
关键修正(相对旧版):
|
||||
- “边缘背景残留 / 内容贴边”改为在 paper_box 裁出的纸面区域上量。
|
||||
旧版量的是 PDF 页面最外圈,而正常出件四周是白边,这两项恒为通过。
|
||||
- 渲染页按文件名数字自然排序,≥10 页不会出现 1,10,2 的顺序。
|
||||
- 渲染后端增加 PyMuPDF(executor 镜像已装 pymupdf),pdftoppm 不在时也能跑。
|
||||
"""
|
||||
import argparse
|
||||
import os
|
||||
@@ -25,23 +16,26 @@ import sys
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
sys.path.insert(0, HERE)
|
||||
from params import P # noqa: E402
|
||||
|
||||
def render(pdf, dpi=100, outdir='.tmp/pdfcheck'):
|
||||
os.makedirs(outdir, exist_ok=True)
|
||||
for f in os.listdir(outdir):
|
||||
if f.startswith('page'):
|
||||
os.remove(os.path.join(outdir, f))
|
||||
base = os.path.join(outdir, 'page')
|
||||
if shutil.which('pdftoppm'):
|
||||
subprocess.run(['pdftoppm', '-r', str(dpi), '-png', pdf, base], check=True)
|
||||
else: # 退路:pypdfium2
|
||||
import pypdfium2 as pdfium
|
||||
doc = pdfium.PdfDocument(pdf)
|
||||
scale = dpi / 72
|
||||
for i in range(len(doc)):
|
||||
doc[i].render(scale=scale).to_pil().save('%s-%d.png' % (base, i + 1))
|
||||
files = sorted(f for f in os.listdir(outdir) if f.startswith('page') and f.endswith('.png'))
|
||||
return [os.path.join(outdir, f) for f in files]
|
||||
|
||||
def _natural_key(path):
|
||||
name = os.path.basename(path)
|
||||
out = []
|
||||
cur = ""
|
||||
for ch in name:
|
||||
if ch.isdigit():
|
||||
cur += ch
|
||||
else:
|
||||
if cur:
|
||||
out.append((1, int(cur)))
|
||||
cur = ""
|
||||
out.append((0, ch.lower()))
|
||||
if cur:
|
||||
out.append((1, int(cur)))
|
||||
return out
|
||||
|
||||
|
||||
def otsu(vals):
|
||||
@@ -55,148 +49,233 @@ def otsu(vals):
|
||||
w1 = total - w0
|
||||
m0 = np.cumsum(hist * centers)
|
||||
mt = m0[-1]
|
||||
with np.errstate(divide='ignore', invalid='ignore'):
|
||||
with np.errstate(divide="ignore", invalid="ignore"):
|
||||
score = (mt * w0 / total - m0) ** 2 / (w0 * w1 / total ** 2)
|
||||
score = np.nan_to_num(score)
|
||||
return float(centers[int(np.argmax(score))])
|
||||
|
||||
|
||||
def analyse(img):
|
||||
g = np.asarray(img.convert('L')).astype(np.float32)
|
||||
def render(pdf, dpi=100, outdir=None):
|
||||
"""把 PDF 逐页渲染成图片,返回按页序排好的文件列表。
|
||||
|
||||
pdftoppm 默认输出 PPM(无损,且不压缩)。之前用 -png 时 zlib 压缩占了
|
||||
整个自检 2 秒里的 2 秒;改 PPM 后像素完全一致,耗时降到 0.1 秒量级。
|
||||
"""
|
||||
outdir = outdir or P["check"]["tmp_dir"]
|
||||
os.makedirs(outdir, exist_ok=True)
|
||||
for f in os.listdir(outdir):
|
||||
if f.startswith("page") and (f.endswith(".png") or f.endswith(".ppm")):
|
||||
try:
|
||||
os.remove(os.path.join(outdir, f))
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
base = os.path.join(outdir, "page")
|
||||
done = False
|
||||
if shutil.which("pdftoppm"):
|
||||
try:
|
||||
subprocess.run(["pdftoppm", "-r", str(dpi), pdf, base],
|
||||
check=True, stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL)
|
||||
done = True
|
||||
except Exception:
|
||||
done = False
|
||||
|
||||
if not done:
|
||||
try:
|
||||
import fitz # PyMuPDF
|
||||
doc = fitz.open(pdf)
|
||||
scale = float(dpi) / 72.0
|
||||
for i, page in enumerate(doc):
|
||||
pix = page.get_pixmap(matrix=fitz.Matrix(scale, scale))
|
||||
pix.save("%s-%d.png" % (base, i + 1))
|
||||
doc.close()
|
||||
except Exception:
|
||||
import pypdfium2 as pdfium
|
||||
doc = pdfium.PdfDocument(pdf)
|
||||
scale = float(dpi) / 72.0
|
||||
for i in range(len(doc)):
|
||||
doc[i].render(scale=scale).to_pil().save(
|
||||
"%s-%d.png" % (base, i + 1))
|
||||
|
||||
files = [os.path.join(outdir, f) for f in os.listdir(outdir)
|
||||
if f.startswith("page") and (f.endswith(".png")
|
||||
or f.endswith(".ppm"))]
|
||||
files.sort(key=_natural_key)
|
||||
return files
|
||||
|
||||
|
||||
def analyse(img, params=None):
|
||||
"""分析一张渲染页,返回纸面框、亮度、边缘与贴边指标。"""
|
||||
c = (params or P)["check"]
|
||||
g = np.asarray(img.convert("L")).astype(np.float32)
|
||||
h, w = g.shape
|
||||
res = {'w': w, 'h': h, 'ratio': w / h}
|
||||
res = {"w": int(w), "h": int(h), "ratio": float(w) / max(1, h)}
|
||||
|
||||
# 纸面亮度:取全图高分位(纸面是主体亮区)
|
||||
res['paper'] = float(np.percentile(g, 80))
|
||||
# 背景亮度:低分位
|
||||
res['back'] = float(np.percentile(g, 2))
|
||||
# 内容区阈值
|
||||
res['ink'] = min(otsu(g), res['paper'] * 0.8)
|
||||
|
||||
# 纸面内容框:A4 页面上纸面之外是纯白留白,故"非纯白"区域即实际纸面
|
||||
# 用相对亮度判定,避免把扫描白纸的轻微灰底误判成内容
|
||||
flat = float(np.percentile(g, 99.5))
|
||||
nonwhite = g < (flat - 8)
|
||||
# 先用“非纯白”找纸面框:PDF 页面四周是白边,纸面被提亮到 ~245
|
||||
flat = float(np.percentile(g, c["flat_pct"]))
|
||||
nonwhite = g < (flat - c["nonwhite_delta"])
|
||||
row_frac = nonwhite.mean(axis=1)
|
||||
col_frac = nonwhite.mean(axis=0)
|
||||
# 取占比超过 5% 的连续范围作为纸面主体
|
||||
rows = np.where(row_frac > 0.05)[0]
|
||||
cols = np.where(col_frac > 0.05)[0]
|
||||
rows = np.where(row_frac > c["paper_row_frac"])[0]
|
||||
cols = np.where(col_frac > c["paper_row_frac"])[0]
|
||||
box = None
|
||||
if rows.size > 4 and cols.size > 4:
|
||||
res['paper_box'] = (int(cols[0]), int(rows[0]), int(cols[-1]), int(rows[-1]))
|
||||
pw = cols[-1] - cols[0] + 1
|
||||
ph = rows[-1] - rows[0] + 1
|
||||
res['paper_ratio'] = pw / ph
|
||||
res['paper_px'] = (int(pw), int(ph))
|
||||
box = (int(cols[0]), int(rows[0]), int(cols[-1]), int(rows[-1]))
|
||||
res["paper_box"] = box
|
||||
res["box_fallback"] = box is None
|
||||
|
||||
if box:
|
||||
x0, y0, x1, y1 = box
|
||||
gp = g[y0:y1 + 1, x0:x1 + 1]
|
||||
else:
|
||||
res['paper_box'] = None
|
||||
res['paper_ratio'] = res['ratio']
|
||||
res['paper_px'] = (w, h)
|
||||
gp = g
|
||||
ph, pw = gp.shape
|
||||
|
||||
# 边缘背景残留:四周窄带的平均亮度明显低于纸面亮度
|
||||
# 边带宽度按比例取,过窄会漏判
|
||||
b = max(4, int(min(w, h) * 0.012))
|
||||
# 透视采样在纸边常带 1~2px 背景毛边,先内缩再量边缘;
|
||||
# 否则会被误判成“边缘背景残留”或“内容贴边”。
|
||||
inset = max(2, int(round(min(pw, ph) * c["edge_inset_frac"])))
|
||||
if pw > 2 * inset + 4 and ph > 2 * inset + 4:
|
||||
gc = gp[inset:-inset, inset:-inset]
|
||||
else:
|
||||
gc = gp
|
||||
gh, gw = gc.shape
|
||||
|
||||
res["paper"] = float(np.percentile(gc, c["paper_pct"]))
|
||||
res["back"] = float(np.percentile(gc, c["back_pct"]))
|
||||
res["ink"] = min(otsu(gc), res["paper"] * c["ink_ratio"])
|
||||
res["paper_ratio"] = float(pw) / max(1, ph)
|
||||
res["paper_px"] = (int(pw), int(ph))
|
||||
|
||||
# 边缘背景残留:在纸面区域的最外圈量,而不是 PDF 白边
|
||||
b = max(4, int(min(gw, gh) * c["border_band_frac"]))
|
||||
border = {
|
||||
'top': float(g[:b, :].mean()), 'bottom': float(g[-b:, :].mean()),
|
||||
'left': float(g[:, :b].mean()), 'right': float(g[:, -b:].mean()),
|
||||
"top": float(gc[:b, :].mean()),
|
||||
"bottom": float(gc[-b:, :].mean()),
|
||||
"left": float(gc[:, :b].mean()),
|
||||
"right": float(gc[:, -b:].mean()),
|
||||
}
|
||||
res['border'] = border
|
||||
res['border_bad'] = [k for k, v in border.items() if v < res['paper'] * 0.80]
|
||||
# 另一路判据:边带内是否存在"整行整列偏暗"的条带(纸外背景)
|
||||
edge_dark = {}
|
||||
for k, band in (('top', g[:b, :]), ('bottom', g[-b:, :]),
|
||||
('left', g[:, :b]), ('right', g[:, -b:])):
|
||||
edge_dark[k] = float((band < res['paper'] * 0.6).mean())
|
||||
res['edge_dark'] = edge_dark
|
||||
res["border"] = border
|
||||
res["border_bad"] = [k for k, v in border.items()
|
||||
if v < res["paper"] * c["border_ratio"]]
|
||||
|
||||
# 内容贴边:最外窄带内成片文字级暗像素 <=> 内容被切
|
||||
m = max(2, int(min(w, h) * 0.003))
|
||||
edge_dark = {}
|
||||
for k, band in (("top", gc[:b, :]), ("bottom", gc[-b:, :]),
|
||||
("left", gc[:, :b]), ("right", gc[:, -b:])):
|
||||
edge_dark[k] = float(
|
||||
(band < res["paper"] * c["edge_dark_ratio"]).mean())
|
||||
res["edge_dark"] = edge_dark
|
||||
|
||||
# 内容贴边:纸面最外窄带内成片文字级暗像素
|
||||
m = max(2, int(min(gw, gh) * c["cut_band_frac"]))
|
||||
cut = []
|
||||
for k, band in (('top', g[:m, :]), ('bottom', g[-m:, :]),
|
||||
('left', g[:, :m]), ('right', g[:, -m:])):
|
||||
frac = float((band < res['ink']).mean())
|
||||
if frac > 0.05:
|
||||
for k, band in (("top", gc[:m, :]), ("bottom", gc[-m:, :]),
|
||||
("left", gc[:, :m]), ("right", gc[:, -m:])):
|
||||
frac = float((band < res["ink"]).mean())
|
||||
if (frac > c["cut_frac"] and
|
||||
float(band.mean()) < res["paper"] * c["cut_mean_ratio"]):
|
||||
cut.append((k, frac))
|
||||
res['cut'] = cut
|
||||
res["cut"] = cut
|
||||
return res
|
||||
|
||||
|
||||
def inspect_pdf(pdf, expect_pages=None, dpi=None, params=None):
|
||||
"""渲染 + 逐页检验,返回结构化结果;渲染失败时 ok=None。"""
|
||||
p = params or P
|
||||
c = p["check"]
|
||||
dpi = int(dpi or c["dpi"])
|
||||
outdir = os.path.join(os.path.dirname(os.path.abspath(pdf)), c["tmp_dir"])
|
||||
try:
|
||||
files = render(pdf, dpi, outdir)
|
||||
except Exception as e:
|
||||
return {"ok": None, "error": str(e), "pages": [], "page_count": None}
|
||||
|
||||
actual = len(files)
|
||||
count_ok = (expect_pages is None) or (actual == expect_pages)
|
||||
out = {
|
||||
"ok": bool(count_ok),
|
||||
"page_count": {"expected": expect_pages, "actual": actual,
|
||||
"ok": bool(count_ok)},
|
||||
"pages": [],
|
||||
}
|
||||
|
||||
# 阈值以 150dpi 出件为基准;check 用的是较低的渲染 dpi,要同时按出件 dpi
|
||||
# 折算,否则选 300dpi 会白白放宽、选 72dpi 会误报“分辨率不足”。
|
||||
render_dpi = float(p["render"]["dpi"])
|
||||
min_short = c["min_short"] * dpi / render_dpi
|
||||
for i, path in enumerate(files, 1):
|
||||
with Image.open(path) as im:
|
||||
r = analyse(im, p)
|
||||
pw, ph = r["paper_px"]
|
||||
short = min(pw, ph)
|
||||
short_ok = short >= min_short
|
||||
border_ok = ((not r["border_bad"]) and
|
||||
all(v <= c["edge_dark_frac"]
|
||||
for v in r["edge_dark"].values()))
|
||||
cut_ok = not r["cut"]
|
||||
dev = (abs(r["paper_ratio"] - r["ratio"]) / r["ratio"]
|
||||
if r["ratio"] else 0.0)
|
||||
|
||||
item = {
|
||||
"index": i,
|
||||
"paper_px": [int(pw), int(ph)],
|
||||
"short_side_px": int(short),
|
||||
"short_side_ok": bool(short_ok),
|
||||
"paper_ratio": round(float(r["paper_ratio"]), 4),
|
||||
"page_ratio": round(float(r["ratio"]), 4),
|
||||
"ratio_dev_pct": round(float(dev * 100), 1),
|
||||
"border_ok": bool(border_ok),
|
||||
"cut_ok": bool(cut_ok),
|
||||
"border": {k: round(float(v), 1) for k, v in r["border"].items()},
|
||||
"edge_dark": {k: round(float(v), 3)
|
||||
for k, v in r["edge_dark"].items()},
|
||||
"cut": [[k, round(float(v), 3)] for k, v in r["cut"]],
|
||||
"box_fallback": bool(r["box_fallback"]),
|
||||
"paper_luma": round(float(r["paper"]), 1),
|
||||
"back_luma": round(float(r["back"]), 1),
|
||||
}
|
||||
out["pages"].append(item)
|
||||
if not (short_ok and border_ok and cut_ok):
|
||||
out["ok"] = False
|
||||
return out
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument('pdf')
|
||||
ap.add_argument('--expect-pages', type=int, default=None)
|
||||
ap.add_argument('--dpi', type=int, default=100)
|
||||
ap.add_argument('--min-short', type=int, default=800)
|
||||
ap.add_argument('--ratio-tol', type=float, default=0.08)
|
||||
ap.add_argument('--render', action='store_true')
|
||||
ap = argparse.ArgumentParser(description="复检已有 PDF(只渲染检验)")
|
||||
ap.add_argument("pdf")
|
||||
ap.add_argument("--expect-pages", type=int, default=None)
|
||||
ap.add_argument("--dpi", type=int, default=P["check"]["dpi"])
|
||||
args = ap.parse_args()
|
||||
|
||||
if not os.path.exists(args.pdf):
|
||||
raise SystemExit('找不到 PDF: %s' % args.pdf)
|
||||
raise SystemExit("找不到 PDF:%s" % args.pdf)
|
||||
|
||||
files = render(args.pdf, args.dpi)
|
||||
print('PDF: %s' % args.pdf)
|
||||
print('文件大小: %.0f KB' % (os.path.getsize(args.pdf) / 1024))
|
||||
print('页数: %d' % len(files))
|
||||
|
||||
ok = True
|
||||
if args.expect_pages is not None:
|
||||
good = len(files) == args.expect_pages
|
||||
ok &= good
|
||||
print(' [%s] 页数与源图一致(期望 %d,实际 %d)'
|
||||
% ('OK' if good else 'XX', args.expect_pages, len(files)))
|
||||
|
||||
for i, f in enumerate(files, 1):
|
||||
img = Image.open(f)
|
||||
r = analyse(img)
|
||||
print('\n第 %d 页 渲染 %dx%d px @%ddpi' % (i, r['w'], r['h'], args.dpi))
|
||||
|
||||
# 纸张实际像素尺寸(按渲染图里纸面外接框估算,换算回原分辨率)
|
||||
if r['paper_box']:
|
||||
x0, y0, x1, y1 = r['paper_box']
|
||||
scale = 1.0 # 渲染已是实际像素
|
||||
short = min(x1 - x0, y1 - y0)
|
||||
good = short >= args.min_short * args.dpi / 150.0
|
||||
ok &= good
|
||||
print(' [%s] 纸面短边 %d px(下限 %d)'
|
||||
% ('OK' if good else 'XX', short,
|
||||
int(args.min_short * args.dpi / 150.0)))
|
||||
|
||||
# 纸张比例本身不是硬性标准:非 A4 材料(Letter / 16K / 票据)
|
||||
# 塞进 A4 页面时必然有留白,纸张比例 != 页面比例是正常的。
|
||||
# 这里只做"提示",判错交给内容贴边与背景残留两项。
|
||||
dev = abs(r['paper_ratio'] - r['ratio']) / r['ratio'] * 100
|
||||
note = '' if dev <= args.ratio_tol else '(留白 %.1f%%,非 A4 纸张属正常)' % dev
|
||||
print(' [--] 纸张比例 %.3f(页面 %.3f)%s'
|
||||
% (r['paper_ratio'], r['ratio'], note))
|
||||
else:
|
||||
print(' [XX] 未能识别纸面区域')
|
||||
ok = False
|
||||
|
||||
bad_dark = [k for k, v in r.get('edge_dark', {}).items() if v > 0.35]
|
||||
good = (not r['border_bad']) and (not bad_dark)
|
||||
ok &= good
|
||||
detail = ', '.join('%s=%.0f' % (k, v) for k, v in r['border'].items())
|
||||
print(' [%s] 边缘背景残留 %s(纸面 %.0f / 背景 %.0f)'
|
||||
% ('OK' if good else 'XX',
|
||||
'无' if good else '、'.join(r['border_bad']), r['paper'], r['back']))
|
||||
if not good:
|
||||
print(' 边带亮度: %s' % detail)
|
||||
if bad_dark:
|
||||
print(' 偏高暗占比: %s'
|
||||
% '、'.join('%s %.0f%%' % (k, r['edge_dark'][k] * 100) for k in bad_dark))
|
||||
|
||||
good = not r['cut']
|
||||
ok &= good
|
||||
print(' [%s] 内容贴边 %s'
|
||||
% ('OK' if good else 'XX',
|
||||
'、'.join('%s %.1f%%' % (k, v * 100) for k, v in r['cut']) if r['cut'] else '无'))
|
||||
|
||||
print('\n总判定:%s' % ('全部通过' if ok else '存在不达标项'))
|
||||
if args.render:
|
||||
print('渲染图: .tmp/pdfcheck/')
|
||||
return 0 if ok else 1
|
||||
r = inspect_pdf(args.pdf, args.expect_pages, args.dpi)
|
||||
print("PDF: %s" % args.pdf)
|
||||
print("文件大小: %.0f KB" % (os.path.getsize(args.pdf) / 1024.0))
|
||||
if r.get("ok") is None:
|
||||
print("渲染失败:%s" % r.get("error"))
|
||||
return 1
|
||||
print("页数: %d" % r["page_count"]["actual"])
|
||||
for item in r["pages"]:
|
||||
print("\n第 %d 页 纸面 %dx%d" % (
|
||||
item["index"], item["paper_px"][0], item["paper_px"][1]))
|
||||
print(" [%s] 纸面短边 %d px"
|
||||
% ("OK" if item["short_side_ok"] else "XX",
|
||||
item["short_side_px"]))
|
||||
print(" [%s] 边缘背景残留 %s"
|
||||
% ("OK" if item["border_ok"] else "XX",
|
||||
"无" if item["border_ok"] else "有"))
|
||||
print(" [%s] 内容贴边 %s"
|
||||
% ("OK" if item["cut_ok"] else "XX",
|
||||
"无" if item["cut_ok"] else
|
||||
"、".join("%s %.1f%%" % (k, v * 100)
|
||||
for k, v in item["cut"])))
|
||||
print(" [--] 纸面比例 %.3f(页面 %.3f)"
|
||||
% (item["paper_ratio"], item["page_ratio"]))
|
||||
print("\n总判定:%s" % ("全部通过" if r["ok"] else "存在不达标项"))
|
||||
return 0 if r["ok"] else 1
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
||||
Reference in New Issue
Block a user