Files
agent/skills/document-photo-to-pdf/doc_deskew/review_page.py
T
kicer a86b748a6f 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。
2026-10-23 23:15:52 +08:00

67 lines
2.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""审核页发布:模板副本 + 每批缩略图,落会话 .app/doc-review/。
模板的单一事实源在 skill 目录的 web/;会话里的 index.html 只是发布副本,
不含任何数据注入。页面运行时通过 /api/db 读 doc_review_* 表,因此同一份
HTML 可服务所有批次。core 只托管会话 .app/,不托管 skill 目录,这是必须
复制一次的原因(不是第二份源码)。
"""
import os
import shutil
from PIL import Image, ImageOps
WEB_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "web")
APP_SUBDIR = os.path.join(".app", "doc-review")
THUMB_LONG = 1200
THUMB_Q = 80
def publish(session_root, batch_id, pages):
"""发布模板与缩略图。
pages: [{idx, source_abs}];返回 (url, thumbs),thumbs[idx] = (相对路径, w, h)。
"""
app_dir = os.path.join(session_root, APP_SUBDIR)
os.makedirs(app_dir, exist_ok=True)
for name in sorted(os.listdir(WEB_DIR)):
src = os.path.join(WEB_DIR, name)
if os.path.isfile(src):
shutil.copy2(src, os.path.join(app_dir, name))
thumb_dir = os.path.join(app_dir, batch_id)
os.makedirs(thumb_dir, exist_ok=True)
thumbs = {}
for p in pages:
src = p.get("source_abs")
idx = p.get("idx")
if not src or idx is None or not os.path.isfile(src):
continue
try:
with Image.open(src) as raw:
im = ImageOps.exif_transpose(raw).convert("RGB")
w, h = im.size
s = min(1.0, float(THUMB_LONG) / max(w, h))
if s < 1.0:
im = im.resize((max(1, int(round(w * s))), max(1, int(round(h * s)))),
Image.LANCZOS)
name = "p%d.jpg" % int(idx)
im.save(os.path.join(thumb_dir, name), "JPEG", quality=THUMB_Q, optimize=True)
thumbs[int(idx)] = (batch_id + "/" + name, im.width, im.height)
except Exception:
continue
task_id = os.path.basename(os.path.abspath(session_root))
return ("/app/%s/doc-review/?b=%s" % (task_id, batch_id), thumbs)
def prune_dirs(session_root, keep_ids):
"""删除不在 keep_ids 里的旧批次缩略图目录(模板文件不动)。"""
root = os.path.join(session_root, APP_SUBDIR)
if not os.path.isdir(root):
return
keep = set(keep_ids)
for name in os.listdir(root):
path = os.path.join(root, name)
if os.path.isdir(path) and name not in keep:
shutil.rmtree(path, ignore_errors=True)