417 lines
16 KiB
Python
417 lines
16 KiB
Python
#!/usr/bin/env python3
|
||
"""文档照片 -> 校正 PDF:全流程串起来的一站式脚本。
|
||
|
||
把原来手工分步的活(网格图 -> 读角点 -> 落盘 -> 回画确认 -> 出 PDF -> 检验)
|
||
压成几条命令,且**产物都落在 out/ 里按序号命名**:
|
||
|
||
out/1-网格-<原图名>.png 每页的坐标网格图(读角点用)
|
||
out/1-角标-<原图名>.png 每页角点回画图(原图 + 网格 + 四角标注,核查是否贴纸边)
|
||
out/1-成品-<原图名>.png 每页矫正后的页面图
|
||
out/corners.json 角点坐标(落盘,跨会话可用)
|
||
out/<名字>.pdf 最终 PDF
|
||
|
||
角点约定(顺序固定,别写反):
|
||
左上 ; 右上 ; 右下 ; 左下 —— 屏幕坐标,原点在图片左上角,单位像素
|
||
|
||
子命令:
|
||
prepare 出网格图 + 生成 corners.json 模板(坐标留空待填)
|
||
set 把某一页的四角坐标写进 corners.json(可反复调用)
|
||
build 回画角标图 + 校验 + 出 PDF + 出成品图 + PDF 检验,一次跑完
|
||
all prepare + build 合体(角点已存在则直接 build)
|
||
check 复检已有 PDF(只渲染检验,不重新出件)
|
||
|
||
典型用法(脚本用绝对路径调用:cwd 是会话任务目录,不是本目录):
|
||
# 1) 出网格图
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py prepare 图1.jpg 图2.jpg
|
||
# 2) 看 out/1-网格-图1.png,把坐标写进文件
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py set "图1.jpg" --quad "150,360;1020,355;1050,1690;90,1660"
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py set "图2.jpg" --quad "120,345;1010,345;1010,1710;120,1710"
|
||
# 3) 一路出 PDF
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py build --out 合同_校正.pdf
|
||
|
||
# 想一步到位(角点已落盘):
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py all 图1.jpg 图2.jpg --out 合同_校正.pdf
|
||
|
||
# 列出 / 检查已落盘角点
|
||
python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py show
|
||
|
||
退出码:0 全部通过;2 角点校验未通过(已出件但需人工判断);3 PDF 检验未通过。
|
||
"""
|
||
import argparse
|
||
import json
|
||
import os
|
||
import re
|
||
import subprocess
|
||
import sys
|
||
|
||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||
sys.path.insert(0, HERE)
|
||
|
||
# 提示里回显的命令:cwd 是会话任务目录,必须用脚本绝对路径,写相对的跑不起来
|
||
SELF = 'python3 ' + os.path.join(HERE, 'pipeline.py')
|
||
|
||
OUT_DIR = 'out'
|
||
CORNERS = os.path.join(OUT_DIR, 'corners.json')
|
||
LABELS = ('左上', '右上', '右下', '左下')
|
||
|
||
IMG_EXT = ('.jpg', '.jpeg', '.png', '.webp', '.bmp', '.tif', '.tiff')
|
||
|
||
|
||
# ---------------------------------------------------------------- 基础工具
|
||
|
||
def natural_key(name):
|
||
return [int(t) if t.isdigit() else t.lower()
|
||
for t in re.split(r'(\d+)', os.path.basename(name))]
|
||
|
||
|
||
def quad_to_str(quad):
|
||
return ';'.join('%g,%g' % (p[0], p[1]) for p in quad)
|
||
|
||
|
||
def load_corners(path=CORNERS):
|
||
if not os.path.exists(path):
|
||
return {}
|
||
with open(path, encoding='utf-8') as f:
|
||
raw = json.load(f)
|
||
out = {}
|
||
for name, v in raw.items():
|
||
if isinstance(v, dict):
|
||
v = v.get('quad') or v.get('corners')
|
||
if not v:
|
||
continue
|
||
out[name] = [(float(p[0]), float(p[1])) for p in v]
|
||
return out
|
||
|
||
|
||
def save_corners(data, path=CORNERS):
|
||
os.makedirs(os.path.dirname(os.path.abspath(path)) or '.', exist_ok=True)
|
||
tmp = path + '.tmp'
|
||
with open(tmp, 'w', encoding='utf-8') as f:
|
||
json.dump({k: [[int(c) if float(c).is_integer() else c for c in p]
|
||
for p in v] for k, v in data.items()},
|
||
f, ensure_ascii=False, indent=2)
|
||
f.write('\n')
|
||
os.replace(tmp, path)
|
||
|
||
|
||
def parse_quad(text):
|
||
quad = []
|
||
for pt in text.replace(';', ';').split(';'):
|
||
pt = pt.strip()
|
||
if not pt:
|
||
continue
|
||
xy = pt.replace(' ', '').split(',')
|
||
if len(xy) != 2:
|
||
raise SystemExit('角点格式不对:%r(应为 x,y)' % pt)
|
||
try:
|
||
quad.append((float(xy[0]), float(xy[1])))
|
||
except ValueError:
|
||
raise SystemExit('角点不是数字:%r' % pt)
|
||
if len(quad) != 4:
|
||
raise SystemExit('角点必须 4 个(左上;右上;右下;左下),实际 %d 个' % len(quad))
|
||
return quad
|
||
|
||
|
||
def collect_images(args):
|
||
"""参数里的图片 + 当前目录全部图片(去重、按自然序)。"""
|
||
names = list(args)
|
||
if not names:
|
||
names = [f for f in os.listdir('.')
|
||
if f.lower().endswith(IMG_EXT) and os.path.isfile(f)]
|
||
seen, out = set(), []
|
||
for n in names:
|
||
if n not in seen:
|
||
seen.add(n)
|
||
out.append(n)
|
||
if not out:
|
||
raise SystemExit('没有找到图片:可在命令后面直接列文件名')
|
||
missing = [n for n in out if not os.path.exists(n)]
|
||
if missing:
|
||
raise SystemExit('图片不存在:%s' % ', '.join(missing))
|
||
return sorted(out, key=natural_key)
|
||
|
||
|
||
def page_tag(i):
|
||
return '%d' % i
|
||
|
||
|
||
def out_path(prefix, i, name, ext='.png'):
|
||
base = os.path.splitext(os.path.basename(name))[0]
|
||
return os.path.join(OUT_DIR, '%s-%s-%s%s' % (page_tag(i), prefix, base, ext))
|
||
|
||
|
||
# ---------------------------------------------------------------- prepare
|
||
|
||
def cmd_prepare(images):
|
||
os.makedirs(OUT_DIR, exist_ok=True)
|
||
from grid import draw_grid
|
||
data = load_corners()
|
||
for i, name in enumerate(images, 1):
|
||
dst = out_path('网格', i, name)
|
||
draw_grid(name, dst)
|
||
data.setdefault(name, None)
|
||
save_corners({k: v for k, v in data.items() if v})
|
||
print('\n网格图已写入 %s/' % OUT_DIR)
|
||
print('下一步:照着网格图读数,把角点写进 %s:' % CORNERS)
|
||
for i, name in enumerate(images, 1):
|
||
print(' %s set "%s" --quad "左上x,左上y;右上x,右上y;'
|
||
'右下x,右下y;左下x,左下y"' % (SELF, name))
|
||
return 0
|
||
|
||
|
||
# ---------------------------------------------------------------- set / show
|
||
|
||
def cmd_set(args):
|
||
"""一次只写一张图:参数是 图片 + 一个 --quad,不批配、不错位。"""
|
||
if '|' in args.image or ':' in args.image:
|
||
raise SystemExit('图片名里不要带 : 或 |:%s' % args.image)
|
||
if not os.path.exists(args.image):
|
||
raise SystemExit('图片不存在:%s' % args.image)
|
||
if len(args.quad) != 1:
|
||
raise SystemExit('set 只能给一个 --quad(实际 %d 个)。一张图一次。'
|
||
% len(args.quad))
|
||
|
||
name = args.image
|
||
quad_s = args.quad[0]
|
||
|
||
data = load_corners()
|
||
old = data.get(name)
|
||
data[name] = parse_quad(quad_s)
|
||
save_corners(data)
|
||
if old is not None:
|
||
print('已更新 %-36s %s(原 %s)'
|
||
% (name, quad_to_str(data[name]), quad_to_str(old)))
|
||
else:
|
||
print('已写入 %-36s %s' % (name, quad_to_str(data[name])))
|
||
print('→ %s(已存:%s)'
|
||
% (CORNERS, '、'.join(sorted(data, key=natural_key))))
|
||
left = [n for n in data if not os.path.exists(n)]
|
||
if left:
|
||
print('[注意] 这些图在 corners.json 里但文件不存在:%s' % '、'.join(left))
|
||
return 0
|
||
|
||
|
||
def cmd_show():
|
||
data = load_corners()
|
||
if not data:
|
||
print('%s 里还没有角点' % CORNERS)
|
||
return 1
|
||
for i, name in enumerate(sorted(data, key=natural_key), 1):
|
||
print('%d. %-40s %s' % (i, name, quad_to_str(data[name])))
|
||
return 0
|
||
|
||
|
||
# ---------------------------------------------------------------- 角标图
|
||
|
||
def draw_marks(name, pts, dst):
|
||
"""把四角画回原图(底图叠加与网格图相同的网格),供人工核查。"""
|
||
from preview_quad import draw_quad
|
||
im = draw_quad(name, pts, with_grid=True)
|
||
im.save(dst)
|
||
return dst
|
||
|
||
|
||
def make_zooms(name, marked_png, idx, zoom):
|
||
"""从角标图上裁出四侧放大块,命名同其它核查图的序号规则。"""
|
||
from PIL import Image
|
||
from preview_quad import zoom_boxes
|
||
im = Image.open(marked_png)
|
||
boxes = zoom_boxes(im, [(0, 0), (im.width, 0), (im.width, im.height), (0, im.height)])
|
||
keys = list(boxes) if zoom == 'all' else [zoom]
|
||
base = os.path.join(OUT_DIR, '%d-角标放大-%s' % (idx, os.path.basename(name)))
|
||
base = os.path.splitext(base)[0]
|
||
for k in keys:
|
||
box = tuple(int(v) for v in boxes[k])
|
||
if box[2] <= box[0] or box[3] <= box[1]:
|
||
continue
|
||
crop = im.crop(box)
|
||
# 细长条按方向切成两段,否则 585x5760 没法看
|
||
segs = []
|
||
if k in ('left', 'right') and crop.height > crop.width * 2.2:
|
||
h = crop.height // 2
|
||
segs = [('上', crop.crop((0, 0, crop.width, h))),
|
||
('下', crop.crop((0, h, crop.width, crop.height)))]
|
||
elif k in ('top', 'bottom') and crop.width > crop.height * 2.2:
|
||
w = crop.width // 2
|
||
segs = [('左', crop.crop((0, 0, w, crop.height))),
|
||
('右', crop.crop((w, 0, crop.width, crop.height)))]
|
||
else:
|
||
segs = [('', crop)]
|
||
for tag, c in segs:
|
||
f = min(3.0, max(1.0, 700.0 / max(1, c.width)))
|
||
if f > 1.0:
|
||
c = c.resize((int(c.width * f), int(c.height * f)), Image.LANCZOS)
|
||
z = '%s-%s%s.png' % (base, k, tag)
|
||
c.save(z)
|
||
print(' 放大块 %s (%dx%d)' % (z, c.width, c.height))
|
||
|
||
|
||
# ---------------------------------------------------------------- build
|
||
|
||
def cmd_build(images, out_pdf, paper, dpi, force, zoom):
|
||
data = load_corners()
|
||
if images:
|
||
names = images
|
||
else:
|
||
names = sorted(data, key=natural_key)
|
||
if not names:
|
||
raise SystemExit('还没有角点。先跑 prepare 出网格图,再用 set 落盘角点。')
|
||
|
||
lacking = [n for n in names if n not in data]
|
||
if lacking:
|
||
raise SystemExit('这些图还没有角点:%s\n先跑 %s set ...'
|
||
% (', '.join(lacking), SELF))
|
||
|
||
os.makedirs(OUT_DIR, exist_ok=True)
|
||
from verify_quad import check as verify_quad
|
||
from run import build, PAPERS
|
||
|
||
ratio = None
|
||
if paper:
|
||
key = paper.strip().lower()
|
||
ratio = PAPERS.get(key)
|
||
if ratio is None:
|
||
try:
|
||
ratio = float(paper)
|
||
except ValueError:
|
||
raise SystemExit('未知纸张:%s(可选 %s 或数字比例)'
|
||
% (paper, '/'.join(PAPERS)))
|
||
|
||
# 1. 角标图 + 校验
|
||
print('=== 步骤 1/4:回画角点(核查用) ===')
|
||
verdicts = []
|
||
for i, name in enumerate(names, 1):
|
||
dst = out_path('角标', i, name)
|
||
draw_marks(name, data[name], dst)
|
||
print('\n第 %d 页 %s → %s' % (i, name, dst))
|
||
ok = verify_quad(name, data[name])
|
||
verdicts.append(ok)
|
||
if zoom:
|
||
make_zooms(name, dst, i, zoom)
|
||
print('\n>>> 请打开上面这些 角标 图,逐个角确认是否压在纸角上。\n')
|
||
|
||
bad_pages = [i for i, ok in enumerate(verdicts, 1) if not ok]
|
||
if bad_pages:
|
||
print('!! 角点校验未通过:第 %s 页(上面标 [XX] 的项)。'
|
||
% '、'.join(map(str, bad_pages)))
|
||
if not force:
|
||
print('已停止,未出件。按上面的提示调整角点,再重跑 set + build。')
|
||
return 2
|
||
print('已按 --force 继续出件:结果需人工确认,不能当作校验通过交付。\n')
|
||
|
||
# 2. 出 PDF
|
||
print('=== 步骤 2/4:透视矫正 + 合成 PDF ===')
|
||
workdir = os.path.join(OUT_DIR, '_pages')
|
||
specs = ['%s:%s' % (n, quad_to_str(data[n])) for n in names]
|
||
pages = build(specs, out_pdf, workdir, ratio)
|
||
|
||
# 成品图按页序号重命名进 out/
|
||
for i, (name, page) in enumerate(zip(names, pages), 1):
|
||
dst = out_path('成品', i, name)
|
||
os.replace(page, dst)
|
||
print(' 成品图 %s' % dst)
|
||
|
||
# 3. PDF 检验
|
||
print('\n=== 步骤 3/4:最终 PDF 检验 ===')
|
||
rc = subprocess.run([sys.executable, os.path.join(HERE, 'check.py'), out_pdf,
|
||
'--dpi', str(dpi), '--expect-pages', str(len(names))]).returncode
|
||
|
||
# 4. 汇总
|
||
bad = bad_pages
|
||
print('\n=== 步骤 4/4:汇总 ===')
|
||
print('PDF :%s(%.0f KB,%d 页)' % (out_pdf, os.path.getsize(out_pdf) / 1024, len(names)))
|
||
print('角点校验 :%s' % ('全部通过' if not bad else '第 %s 页未通过' % '、'.join(map(str, bad))))
|
||
print('PDF 检验 :%s' % ('通过' if rc == 0 else '未通过'))
|
||
print('核查材料 :')
|
||
for i, name in enumerate(names, 1):
|
||
print(' %s %s %s' % (out_path('网格', i, name), out_path('角标', i, name),
|
||
out_path('成品', i, name)))
|
||
if bad or rc != 0:
|
||
print('注意:以上为原样结果,未做任何自动修正。')
|
||
return 2 if bad else 3
|
||
return 0
|
||
|
||
|
||
# ---------------------------------------------------------------- check
|
||
|
||
def cmd_check(pdf, expect_pages, dpi):
|
||
"""复检已有 PDF:只渲染检验,不重新校正、不改动文件。"""
|
||
if not os.path.exists(pdf):
|
||
raise SystemExit('找不到 PDF:%s' % pdf)
|
||
cmd = [sys.executable, os.path.join(HERE, 'check.py'), pdf, '--dpi', str(dpi)]
|
||
if expect_pages is not None:
|
||
cmd += ['--expect-pages', str(expect_pages)]
|
||
return subprocess.run(cmd).returncode
|
||
|
||
|
||
# ---------------------------------------------------------------- main
|
||
|
||
def main():
|
||
ap = argparse.ArgumentParser(
|
||
description='文档照片 -> 校正 PDF 全流程脚本',
|
||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||
epilog=__doc__)
|
||
sub = ap.add_subparsers(dest='cmd', required=True)
|
||
|
||
p = sub.add_parser('prepare', help='出网格图(out/1-网格-*.png)')
|
||
p.add_argument('images', nargs='*', help='图片名,省略则取当前目录所有图片')
|
||
|
||
p = sub.add_parser('set', help='把一张图的角点写进 out/corners.json')
|
||
p.add_argument('image', metavar='IMG', help='图片名(一次一张)')
|
||
p.add_argument('--quad', action='append', default=[], required=True,
|
||
metavar='左上x,左上y;右上x,右上y;右下x,右下y;左下x,左下y',
|
||
help='这一张图的四个角点(顺序固定:左上 右上 右下 左下)')
|
||
|
||
p = sub.add_parser('show', help='查看已落盘角点')
|
||
|
||
p = sub.add_parser('check', help='复检已有 PDF(只渲染检验,不重新出件)')
|
||
p.add_argument('pdf', metavar='PDF')
|
||
p.add_argument('--expect-pages', type=int, default=None)
|
||
p.add_argument('--dpi', type=int, default=100)
|
||
|
||
p = sub.add_parser('build', help='回画角标 + 校验 + 出 PDF + 检验')
|
||
p.add_argument('images', nargs='*', help='图片名,省略则用 corners.json 里的全部')
|
||
p.add_argument('--out', default='文档_校正.pdf')
|
||
p.add_argument('--paper', default=None, help='a4/letter/16k/b5 或比例数字')
|
||
p.add_argument('--dpi', type=int, default=100, help='PDF 检验渲染 dpi')
|
||
p.add_argument('--force', action='store_true', help='角点校验不通过也继续')
|
||
p.add_argument('--zoom', default=None,
|
||
choices=['left', 'right', 'top', 'bottom', 'all'],
|
||
help='另存边角放大块,便于细看')
|
||
|
||
p = sub.add_parser('all', help='prepare + build 一步到位')
|
||
p.add_argument('images', nargs='*')
|
||
p.add_argument('--out', default='文档_校正.pdf')
|
||
p.add_argument('--paper', default=None)
|
||
p.add_argument('--dpi', type=int, default=100)
|
||
p.add_argument('--force', action='store_true')
|
||
p.add_argument('--zoom', default=None)
|
||
|
||
args = ap.parse_args()
|
||
|
||
if args.cmd == 'prepare':
|
||
return cmd_prepare(collect_images(args.images))
|
||
if args.cmd == 'set':
|
||
return cmd_set(args)
|
||
if args.cmd == 'show':
|
||
return cmd_show()
|
||
if args.cmd == 'check':
|
||
return cmd_check(args.pdf, args.expect_pages, args.dpi)
|
||
if args.cmd == 'build':
|
||
imgs = collect_images(args.images) if args.images else []
|
||
return cmd_build(imgs, args.out, args.paper, args.dpi, args.force, args.zoom)
|
||
if args.cmd == 'all':
|
||
imgs = collect_images(args.images)
|
||
cmd_prepare(imgs)
|
||
data = load_corners()
|
||
lacking = [n for n in imgs if n not in data]
|
||
if lacking:
|
||
print('\n这些图还没有角点,填好后重跑 build:%s' % ', '.join(lacking))
|
||
return 2
|
||
return cmd_build(imgs, args.out, args.paper, args.dpi, args.force, args.zoom)
|
||
return 1
|
||
|
||
|
||
if __name__ == '__main__':
|
||
sys.exit(main())
|