Files
cad-agent/dwg_review/phases/evidence.py
T

309 lines
12 KiB
Python
Raw Normal View History

"""阶段 2:逐审查单元取证(多源证据层 + 视觉多图)。
对每个审查单元:取结构化数据(实体/文字/标注/块/多段线)+ 视觉截图(整体 + 可选局部)。
结构化数据是权威依据,截图仅作视觉上下文。
多源设计:`collect()` 按审查单元来源分发;当前仅实现 CAD 源,PDF / 图片源预留 seam
(未来在对应分支产出**同形** evidence,下游无需改动)。
"""
import contextlib
import math
import time
from .. import config, evidence_model, heatmap, sources, tiling
from ..llm_client import image_size_b64
from ..mcp_client import result_images, result_json
_LABEL_OVERALL = "overall"
# 绘图区最大化用的工具名(旧版插件没有此工具 → 静默降级)
_TOOL_DRAWING_AREA = "set_drawing_area"
# zoom 时四周留边比例(与 `zoom_to_window` 的默认 margin 一致)
_ZOOM_MARGIN = 0.02
@contextlib.contextmanager
def maximized_drawing_area(ctx):
"""截屏前最大化绘图区(窗口铺满屏幕 + 干净屏幕),退出时还原。
实测绘图区像素 2110x462 → 3310x1084(3.68x);在同样的长边下采样预算下,
有效像素更多、细节更清楚,自适应瓦片张数也更少。
- 受 `config.DRAWING_AREA_MAXIMIZE` 控制;
- 工具不存在(旧版插件)/ 调用失败 → **静默降级**:照常取证,只是绘图区小一些;
- 退出时一定尝试还原;**还原失败不掩盖业务异常**(不 raise)。
- 离线源(PDF / 图片)无 CAD 连接(`ctx.tools is None`)→ 直接放行。
"""
if not config.DRAWING_AREA_MAXIMIZE or ctx.tools is None:
yield
return
entered = False
try:
if ctx.tools.has(_TOOL_DRAWING_AREA):
ctx.tools.call(_TOOL_DRAWING_AREA, {"mode": "max"})
entered = True
time.sleep(config.DRAWING_AREA_ENTER_WAIT)
except Exception: # noqa: BLE001 - 界面优化失败不应中断审查
entered = False
try:
yield
finally:
if entered:
try:
ctx.tools.call(_TOOL_DRAWING_AREA, {"mode": "restore"})
time.sleep(config.DRAWING_AREA_RESTORE_WAIT)
except Exception: # noqa: BLE001
pass
def bbox_to_window(bbox):
"""[minx,miny,maxx,maxy] -> window 对象。"""
return {
"min_x": float(bbox[0]),
"min_y": float(bbox[1]),
"max_x": float(bbox[2]),
"max_y": float(bbox[3]),
}
def sub_windows(window, tiles):
"""把 window 等分为 tiles 个子窗口(tiles=4 → 2x2 象限)。
tiles<=1 返回 []。返回 [{"min_x",..,"max_x",..}, ...],行优先(左上→右上→左下→右下)。
"""
if not tiles or tiles <= 1:
return []
cols = int(math.ceil(math.sqrt(tiles)))
rows = int(math.ceil(tiles / cols))
min_x, min_y = window["min_x"], window["min_y"]
max_x, max_y = window["max_x"], window["max_y"]
w = (max_x - min_x) / cols
h = (max_y - min_y) / rows
out = []
for r in range(rows):
for c in range(cols):
if len(out) >= tiles:
break
out.append(
{
"min_x": min_x + c * w,
"min_y": max_y - (r + 1) * h,
"max_x": min_x + (c + 1) * w,
"max_y": max_y - r * h,
}
)
return out
def zoom_and_shot(ctx, window, margin=_ZOOM_MARGIN):
"""缩放到窗口、等待渲染、截一张图,返回 (b64, mime) 或 None。"""
ctx.tools.call("zoom_to_window", dict(window, margin=margin))
time.sleep(config.RENDER_WAIT)
shot = ctx.tools.call("get_viewport_screenshot", {})
images = result_images(shot)
if not images:
return None
return images[0]
def _is_truncated(*envelopes):
"""任一信封 `total > len(items)` 即视为**被截断**(数据不全)。"""
for env in envelopes:
if not isinstance(env, dict):
continue
items = env.get("items")
if not isinstance(items, list):
continue
try:
total = int(env.get("total") or len(items))
except (TypeError, ValueError):
total = len(items)
if total > len(items):
return True
return False
def _text_boxes(entities, texts, dimensions):
"""收集「文字类」实体 bbox。
标准文字 / 标注信封(`get_text_content` / `get_dimensions`)全收;
再加**类名含 text/label/dim 等关键词**的自定义实体(`tiling.is_text_type`)。
"""
boxes = list(heatmap.entity_boxes(texts))
boxes.extend(heatmap.entity_boxes(dimensions))
items = entities.get("items") if isinstance(entities, dict) else None
for it in items or []:
if isinstance(it, dict) and tiling.is_text_type(it.get("type")):
b = heatmap.norm_box(it.get("bbox"))
if b is not None:
boxes.append(b)
return boxes
def _content_predicate(boxes):
"""构造「该窗口内是否有实体」谓词;无实体返回 None(委托 `tiling.content_predicate`)。"""
return tiling.content_predicate(boxes)
def _apply_keep(regions, keep):
"""按 keep 过滤窗口;过滤后为空则**退回原集合**(宁可多拍也不漏)。"""
if keep is None or not regions:
return regions
kept = [w for w in regions if keep(w)]
return kept or regions
def _plan_tiles(window, frame, boxes, text_boxes, truncated, view_px):
"""尝试按实体分布规划瓦片窗口;任何条件不满足都返回 [](调用方退回固定策略)。
降级条件:规划被关闭 / 实体数据被截断 / 缺图框 / 无实体 / 拿不到绘图区像素 /
比例未知(`frame_scale` 返 0)。
"""
if not config.TILING_ENABLED or truncated or not frame or not boxes or not view_px:
return []
scale = tiling.frame_scale(frame)
s_text = tiling.world_per_px(scale, config.TEXT_HEIGHT_MM, config.TEXT_READABLE_PX)
# 线条区只需看清走向:同以「最小关注特征尺寸」(纸面 TEXT_HEIGHT_MM)为基准,
# 但像素门槛更低(R_line < R_text)→ 覆盖范围更大、瓦片更少。
s_line = tiling.world_per_px(scale, config.TEXT_HEIGHT_MM, config.LINE_READABLE_PX)
if s_text <= 0 or s_line <= 0:
return []
eff = tiling.effective_px(view_px, config.IMAGE_MAX_EDGE)
if eff[0] <= 0 or eff[1] <= 0:
return []
cell = heatmap.div_to_cell(window, config.HEATMAP_CELL_DIV)
grid = heatmap.build_grid(window, boxes, cell)
clusters = heatmap.cluster_cells(grid, dilate=config.HEATMAP_CLUSTER_DILATE)
if not clusters:
return []
flags = tiling.cluster_text_flags(clusters, text_boxes)
text_idx = {i for i, is_text in enumerate(flags) if is_text}
return tiling.plan_regions(
frame, clusters,
text_clusters=text_idx, s_text=s_text, s_line=s_line, view_px=eff,
max_tiles=config.TILE_MAX_COUNT, overlap=config.TILE_OVERLAP,
keep=_content_predicate(boxes),
)
def capture_images(ctx, window, *, tiles=0, max_images=None, frame=None,
boxes=None, text_boxes=None, truncated=False):
"""采集视觉证据:整体一张 + 局部若干张(自适应瓦片优先,否则等分象限回退)。
- 整体 label="overall",局部 label="tile-1"..;行优先。
- 局部窗口优先由 `_plan_tiles` 按**实体分布**给出(空白区不出图);
不可用时退回 `sub_windows(window, tiles)`,**同样按内容过滤**空白象限
(过滤后为空则退回未过滤集合,保证不漏拍)。
- 每张图登记其**实际可见世界范围**(`window` 字段)——审查阶段的 `inspect_region`
靠它把「截图上的归一化坐标」映射回 WCS(逐级下钻)。
- 结束时**复位到整体视口**,保证后续流程从整幅视图起手。
- 受 max_images(默认 config.EVIDENCE_MAX_IMAGES)截断。
"""
if max_images is None:
max_images = config.EVIDENCE_MAX_IMAGES
images = []
# 整体图:既是证据,也用于测量绘图区**实际像素**(决定单张截图的世界覆盖范围)
overall = zoom_and_shot(ctx, window)
view_px = image_size_b64(overall[0]) if overall else None
def _add(shot, label, win):
"""登记截图;`win` 为送给 CAD 的窗口,用于反算实际可见世界范围。"""
if shot and len(images) < max_images:
images.append(
evidence_model.make_image(
shot[0], shot[1], label,
window=tiling.visible_box(
tiling.window_to_box(win), view_px, _ZOOM_MARGIN
),
)
)
_add(overall, _LABEL_OVERALL, window)
# 内容过滤:空白区不出图。按**实体 bbox** 判定,规划与回退两条路径共用同一谓词;
# 实体数据被截断时不可信,放弃过滤(宁可多拍也不漏)。
keep = None if truncated else _content_predicate(boxes)
# 局部:优先自适应瓦片,失败退回等分象限(回退路径同样按内容过滤)
regions = _plan_tiles(window, frame, boxes, text_boxes, truncated, view_px)
if not regions:
regions = _apply_keep(sub_windows(window, tiles), keep)
for i, sub in enumerate(regions, 1):
if len(images) >= max_images:
break
_add(zoom_and_shot(ctx, sub), f"tile-{i}", sub)
# 复位整体视口(不截图)
ctx.tools.call("zoom_to_window", dict(window, margin=_ZOOM_MARGIN))
return images
def collect_frame(ctx, index, frame):
"""采集单个图框(CAD 源)的证据;bbox 无效时返回 None。"""
bbox = frame.get("bbox")
if not bbox or len(bbox) != 4:
return None
win = bbox_to_window(bbox)
limit = ctx.frame_limit
# a. 结构化数据(权威;按 window 查询,不依赖缩放)
entities = result_json(ctx.tools.call("query_entities", {"window": win, "limit": limit}), {})
texts = result_json(ctx.tools.call("get_text_content", {"window": win, "limit": limit}), {})
dimensions = result_json(ctx.tools.call("get_dimensions", {"window": win, "limit": limit}), {})
blocks = result_json(
ctx.tools.call("get_block_references", {"window": win, "limit": limit}), {}
)
polylines = result_json(
ctx.tools.call("get_polylines_info", {"window": win, "limit": limit}), {}
)
# b. 视觉:整体 + 局部(优先按实体分布自适应瓦片;数据截断则退回固定策略)
truncated = _is_truncated(entities, texts, dimensions, blocks, polylines)
boxes = heatmap.drop_oversized(
heatmap.entity_boxes(entities), win, config.HEATMAP_MAX_AREA_FRAC
)
images = capture_images(
ctx, win,
tiles=config.EVIDENCE_DETAIL_TILES,
frame=frame,
boxes=boxes,
text_boxes=_text_boxes(entities, texts, dimensions),
truncated=truncated,
)
return {
"source_type": evidence_model.source_type_of(frame),
"index": index,
"frame": frame,
"window": win,
"entities": entities,
"texts": texts,
"dimensions": dimensions,
"blocks": blocks,
"polylines": polylines,
"images": images,
}
def collect(ctx, index, unit):
"""按审查单元来源分发取证。
CAD 源走 `collect_frame`(CAD 工具 + 截屏);PDF / 图片源走 `sources.collect`
(内存渲染 + 墨迹瓦片),产出与 CAD **同形**的 evidence:`window` 有值、
结构化键给空信封(PDF 另有 best-effort 文本层)、`images` 带 label。
"""
source = evidence_model.source_type_of(unit)
if source == evidence_model.SOURCE_CAD:
return collect_frame(ctx, index, unit)
if sources.is_file_source(source):
return sources.collect(ctx, index, unit)
return None