# -*- coding: utf-8 -*- """state.json v2 与 edits.json:归一化坐标、页面状态分级、编辑覆盖。 坐标约定 -------- corners_norm / edits 里的 "c" 一律是归一化 0~1,相对 exif_transpose 之后的 **原图**:[[x_tl,y_tl],[x_tr,y_tr],[x_br,y_br],[x_bl,y_bl]]。 原图像素坐标只在检测、渲染时用;进出 state 一律换成归一化, 换预览分辨率、换 UI 画布都不会错位。 页面状态(取代"整批失败") -------------------------- ready 已就绪,无需人看 review 建议看一眼(掩膜回退角点、覆盖率低、纸型存疑) needs_orientation 宽高比接近正方形,横竖判不出来,需要人点旋转 needs_corners 必须补角(检测为空、框内纸面占比过低) render_failed 出页失败,已用白页占位(极少见) failed 原图打不开,本页已跳过(传错文件) deleted 人主动删掉的页,不进出件 严重度只用来决定"一页命中多条规则时记哪一条",不参与任何几何计算。 """ import json import os STATE_SCHEMA = "document-photo-to-pdf/2" EDITS_SCHEMA = "review/1" # 顺序即严重度,越靠后越需要人介入 STATUS_ORDER = ["ready", "review", "needs_orientation", "needs_corners", "render_failed", "failed", "deleted"] _SEV = {s: i for i, s in enumerate(STATUS_ORDER)} # ---------------------------------------------------------------- 坐标 def norm_quad(quad, size): """原图像素坐标 -> 归一化 0~1(4 位小数,300dpi 往返误差远小于 1px)。""" w = float(size[0]) or 1.0 h = float(size[1]) or 1.0 return [[round(float(p[0]) / w, 4), round(float(p[1]) / h, 4)] for p in quad] def denorm_quad(norm, size): """归一化 0~1 -> 原图像素坐标。""" w, h = float(size[0]), float(size[1]) return [[float(p[0]) * w, float(p[1]) * h] for p in norm] # ---------------------------------------------------------------- 状态 def escalate(status, reason, cand, cand_reason): """取更严重的一对 (status, reason);同级保留先到的。""" if _SEV.get(cand, 0) > _SEV.get(status, 0): return cand, cand_reason return status, reason def grade_page(meta, P, ref_ratio=None): """按方案第 6 节的表,把一页的检测数字转成"要不要人看"。 纯路由:不重新检测、不改数字,只决定这一页在审核页上标不标 `!`。 ref_ratio 是这张纸应有的宽高比(竖版为正);None 表示未知,跳过纸型判断。 """ g = P["gate"] dead = g["aspect_deadband"] status, reason = "ready", None if meta.get("fallback"): status, reason = escalate(status, reason, "review", "mask_fallback") cov = meta.get("coverage") or {} if cov and min(float(v) for v in cov.values()) < g["coverage_warn"]: status, reason = escalate(status, reason, "review", "low_coverage") metrics = (meta.get("validation") or {}).get("metrics") or {} frac = metrics.get("inner_paper_frac") if frac is not None and float(frac) <= g["inner_paper_min"]: status, reason = escalate(status, reason, "needs_corners", "inner_paper_low") aspect = meta.get("aspect") if aspect: if abs(float(aspect) - 1.0) <= dead: # 横竖看不出来:不猜,交给人点旋转 status, reason = escalate(status, reason, "needs_orientation", "aspect_ambiguous") elif ref_ratio: # 同向折算后再比:横放的 A4 不该被判成异形纸 r = float(ref_ratio) if float(aspect) > 1.0: r = 1.0 / r if r > 0 else r dev = abs(float(aspect) - r) / r if r > 0 else 0.0 if dev > g["paper_mismatch_pct"] / 100.0: status, reason = escalate(status, reason, "review", "paper_mismatch") return status, reason # ---------------------------------------------------------------- edits def _quad_ok(c): """校验归一化四边形:4 点、每点 2 数、范围放宽到 -1~2(角点允许拖出画面)。""" if not isinstance(c, (list, tuple)) or len(c) != 4: return None out = [] for p in c: if not isinstance(p, (list, tuple)) or len(p) != 2: return None try: x, y = float(p[0]), float(p[1]) except (TypeError, ValueError): return None # 方案第 11 节:纸被切掉一块时角点必须能拖到画面外,所以下限放到 -1 if not (-1.0 <= x <= 2.0 and -1.0 <= y <= 2.0): return None out.append([x, y]) return out def _rot_ok(v): """旋转角归一到 0/90/180/270,认不出来按 0(不转)处理。""" try: r = int(round(float(v))) % 360 except (TypeError, ValueError): return 0 return r if r in (0, 90, 180, 270) else 0 def load_edits(value): """把 edits.json 读成内部结构;value 是路径、dict 或 None。 只校验结构与范围,不认识的多余字段一律忽略——前端的版本总比后端快, 不该因为多了一个字段就拒绝出件。 """ if value is None or value == "" or value == {}: return None if isinstance(value, str): path = os.path.abspath(os.path.expanduser(value.strip())) if not os.path.isfile(path): raise ValueError("edits 文件不存在:%s" % path) with open(path, "r", encoding="utf-8") as f: value = json.load(f) if not isinstance(value, dict): raise ValueError("edits 必须是 JSON 对象或 edits.json 路径") batch = value.get("batch") batch = dict(batch) if isinstance(batch, dict) else {} pages = {} for item in (value.get("pages") or []): if not isinstance(item, dict): continue try: idx = int(item.get("i")) except (TypeError, ValueError): continue if idx < 1: continue rec = {} q = _quad_ok(item.get("c")) if q: rec["corners_norm"] = q if item.get("r") is not None: rec["rotate"] = _rot_ok(item.get("r")) if rec: pages[idx] = rec order = [] for v in (value.get("order") or []): try: order.append(int(v)) except (TypeError, ValueError): continue # order 缺省/为空 = 按 images 传入顺序出件,调用方自己兜底 deleted = set() for v in (value.get("deleted") or []): try: deleted.add(int(v)) except (TypeError, ValueError): continue return {"schema": EDITS_SCHEMA, "batch": batch, "pages": pages, "order": order, "deleted": deleted} # ---------------------------------------------------------------- state v2 _STATE_PAGE_KEYS = ("index", "source", "source_size", "auto_corners", "corners_norm", "rotate", "rotate_source", "status", "reason") def build_state(batch, pages): """state.json v2:只放重建这次结果需要的东西,不放 PDF 检验数据。 pages 项由调用方组装好,这里只裁字段、保顺序,不再做判断。 """ return { "schema": STATE_SCHEMA, "batch": { "doc_type": batch.get("doc_type"), "paper": batch.get("paper"), "enhance": batch.get("enhance"), "dpi": batch.get("dpi"), "orientation": batch.get("orientation"), }, "pages": [{k: p.get(k) for k in _STATE_PAGE_KEYS} for p in pages], } def load_state(value): """读上一份 state v2(可选输入):按 index 取 auto_corners,供"恢复自动"。 缺文件、旧 schema、字段不全都当成没传——state 是参考,不是契约。 """ if value in (None, ""): return {} try: if isinstance(value, str): path = os.path.abspath(os.path.expanduser(value.strip())) if not os.path.isfile(path): return {} with open(path, "r", encoding="utf-8") as f: value = json.load(f) if not isinstance(value, dict) or value.get("schema") != STATE_SCHEMA: return {} out = {} for item in (value.get("pages") or []): if isinstance(item, dict) and item.get("index") is not None: out[int(item["index"])] = item return out except Exception: return {}