gjm
b757892c67
解决三个缺口：① 放大没复用标定/瓦片数学（LLM 一次 zoom 只出一张，宽区域仍读不清）；
②「看清没」由 VLM 自评（易过度自信/幻觉）；③ 只能按 handle / 手算 bbox 指认，
图上看到但没 handle 的东西指认不了。
核心思路：把「放大」升级成一个语义化工具——LLM 只指认「要看哪里」，由 agent 复用
tiling.py 的标定数学算出该切几张、每张覆盖多大，用构造保证可读。
新增 dwg_review/inspect.py（agent 侧，不编 DLL）：
- TOOL_SCHEMA：inspect_region(target, purpose)；target 三形态 {handle} / {window} /
{label,cx,cy,span}，purpose = text(8px) / line(6px)。
- InspectState：单图框内「截图标签 → 世界可见范围」登记表，支持逐级下钻
（返回的 inspect-N 可继续作为 label 指认）。
- resolve_target / _point_box：label+cx+cy → WCS。cy 是图像坐标（上→下），
世界 y 必须翻转（y = y2 - cy*H）——单测专门钉住。
- plan_tiles：复用 world_per_px + tiles_for_box + subdivide；超 INSPECT_MAX_TILES(4)
则硬失败并给出「缩小 target / 分多次请求」的指引（不静默降级）；拿不到比例/像素
则退回单张并如实告知。
关键几何：CAD 的 _.ZOOM _W 是等比适配（不拉伸），故「截图上的归一化坐标」必须按
max(W/ew, H/eh) 反算真实可见范围（新增 tiling.visible_box）——直接用送进去的窗口会偏。
zoom_to_window 返回的 view 是「加过 margin 的窗口」，不是可见范围，不能混用。
证据层配套：evidence_model.make_image(..., window=) 记录每张图的可见世界范围；
capture_images 用 view_px（overall 图原始像素）+ visible_box 逐张登记。
子循环接入：_run_readonly_tool 在只读白名单校验之前拦截 inspect_region（它不在
READ_ONLY_TOOLS 里，内部只调白名单内的只读 MCP 工具）；_review_tools 启用时用
inspect_region 取代三个裸视口工具；inspect_region 计入 _VIEW_TOOLS → 结束复位视口。
配置：INSPECT_ENABLED(True) / INSPECT_MAX_TILES(4)。
端到端实测（真实图纸 1 图框）：取证与审查两阶段均在最大化态、结束精确还原（4 项 PASS）；
LLM 的 11 次取证调用里 2 次是 inspect_region，且都显式给 window + purpose:"text"
（x[20000,115000] y[-6500,3000]，即 A0 图框底部横条＝标题栏所在）。
验收口径达成：报告报出标题栏乱码 ???????????????，而 get_text_content 对全图返回 0 条文字
（本图文字全在块/自定义实体内）→ 块内文字是被视觉放大读出来的。
pytest 343 passed。
283 lines
11 KiB
Python
283 lines
11 KiB
Python
"""`dwg_review.tiling` 单元测试（纯函数，不依赖 CAD / LLM / Pillow）。"""
|
||
|
||
import pytest
|
||
|
||
from dwg_review import tiling as tl
|
||
|
||
|
||
def _frame(bbox, sheet_size="A0", sheet_scale=0.0):
|
||
return {"bbox": list(bbox), "sheet_size": sheet_size, "sheet_scale": sheet_scale}
|
||
|
||
|
||
def _cluster(bbox, count=10):
|
||
return {"bbox": tuple(float(v) for v in bbox), "cells": [], "count": count}
|
||
|
||
|
||
# --- norm_box / frame_bbox --------------------------------------------------
|
||
|
||
def test_norm_box_valid_and_invalid():
|
||
assert tl.norm_box([0, 0, 10, 20]) == (0.0, 0.0, 10.0, 20.0)
|
||
assert tl.norm_box([10, 20, 0, 0]) == (0.0, 0.0, 10.0, 20.0)
|
||
assert tl.norm_box([1, 2, 3]) is None
|
||
assert tl.norm_box(None) is None
|
||
assert tl.norm_box([0, 0, float("nan"), 1]) is None
|
||
|
||
|
||
def test_frame_bbox_rejects_degenerate_and_non_dict():
|
||
assert tl.frame_bbox(_frame((0, 0, 100, 50))) == (0.0, 0.0, 100.0, 50.0)
|
||
assert tl.frame_bbox(_frame((0, 0, 0, 50))) is None # 零宽
|
||
assert tl.frame_bbox(_frame((0, 0, 100, 0))) is None # 零高
|
||
assert tl.frame_bbox({"bbox": [1, 2, 3]}) is None
|
||
assert tl.frame_bbox(None) is None
|
||
|
||
|
||
def test_frame_world_size():
|
||
assert tl.frame_world_size(_frame((0, 0, 100, 50))) == (100.0, 50.0)
|
||
assert tl.frame_world_size(_frame((0, 0, 0, 0))) == (0.0, 0.0)
|
||
|
||
|
||
# --- frame_scale：三条路径 --------------------------------------------------
|
||
|
||
def test_frame_scale_prefers_sheet_scale():
|
||
assert tl.frame_scale(_frame((0, 0, 100, 50), sheet_scale=100.0)) == 100.0
|
||
|
||
|
||
def test_frame_scale_derived_landscape():
|
||
# A0 横放：世界 118900 x 84100 → 118900/1189 = 100
|
||
f = _frame((0, 0, 118900, 84100), sheet_size="A0")
|
||
assert tl.frame_scale(f) == 100.0
|
||
|
||
|
||
def test_frame_scale_derived_portrait():
|
||
# A0 纵放：世界宽 ↔ 纸高 841
|
||
f = _frame((0, 0, 84100, 118900), sheet_size="A0")
|
||
assert tl.frame_scale(f) == 100.0
|
||
|
||
|
||
def test_frame_scale_falls_back_to_default():
|
||
assert tl.frame_scale(_frame((0, 0, 100, 50), sheet_size="ZZ"), default=7.0) == 7.0
|
||
assert tl.frame_scale(_frame((0, 0, 0, 0)), default=7.0) == 7.0
|
||
assert tl.frame_scale(None, default=7.0) == 7.0
|
||
|
||
|
||
# --- effective_px / world_per_px -------------------------------------------
|
||
|
||
def test_effective_px_no_resize_when_small():
|
||
assert tl.effective_px((800, 600), 1280) == (800, 600)
|
||
|
||
|
||
def test_effective_px_downsamples_long_edge():
|
||
# 实测 CAD 绘图区 2110x462 → 长边缩到 1280
|
||
assert tl.effective_px((2110, 462), 1280) == (1280, 280)
|
||
|
||
|
||
def test_effective_px_invalid():
|
||
assert tl.effective_px(None, 1280) == (0, 0)
|
||
assert tl.effective_px((0, 100), 1280) == (0, 0)
|
||
assert tl.effective_px((100, 100), 0) == (100, 100) # 0 = 不缩放
|
||
|
||
|
||
def test_world_per_px():
|
||
# 1:100、纸面 2mm、VLM 需 10px → 每像素 20 图形单位
|
||
assert tl.world_per_px(100.0, 2.0, 10.0) == 20.0
|
||
assert tl.world_per_px(0, 2.0, 10.0) == 0.0
|
||
assert tl.world_per_px(100.0, 2.0, 0) == 0.0
|
||
|
||
|
||
# --- is_text_type -----------------------------------------------------------
|
||
|
||
def test_is_text_type_standard():
|
||
for t in ("TEXT", "MTEXT", "ATTRIB", "ATTDEF", "DIMENSION", "text"):
|
||
assert tl.is_text_type(t) is True
|
||
|
||
|
||
def test_is_text_type_custom_keywords():
|
||
for t in ("AECDLABEL", "AECDDIMTEXT", "MYNOTE", "PARTTAG", "ANNOTATION", "TITLEBLK"):
|
||
assert tl.is_text_type(t) is True
|
||
|
||
|
||
def test_is_text_type_negative():
|
||
for t in ("AECDBEWPIPE", "LINE", "LWPOLYLINE", "INSERT", "HATCH", "", None, 123):
|
||
assert tl.is_text_type(t) is False
|
||
|
||
|
||
# --- 相交 / 文字簇标记 -------------------------------------------------------
|
||
|
||
def test_boxes_intersect():
|
||
assert tl.boxes_intersect((0, 0, 10, 10), (5, 5, 15, 15)) is True
|
||
assert tl.boxes_intersect((0, 0, 10, 10), (10, 10, 20, 20)) is True # 接触算相交
|
||
assert tl.boxes_intersect((0, 0, 10, 10), (11, 11, 20, 20)) is False
|
||
assert tl.boxes_intersect(None, (0, 0, 1, 1)) is False
|
||
|
||
|
||
def test_cluster_text_flags():
|
||
clusters = [_cluster((0, 0, 10, 10)), _cluster((100, 100, 110, 110))]
|
||
flags = tl.cluster_text_flags(clusters, [(5, 5, 6, 6)])
|
||
assert flags == [True, False]
|
||
assert tl.cluster_text_flags(clusters, []) == [False, False]
|
||
assert tl.cluster_text_flags([], [(0, 0, 1, 1)]) == []
|
||
|
||
|
||
# --- tiles_for_box / subdivide ---------------------------------------------
|
||
|
||
def test_tiles_for_box_fits_single():
|
||
assert tl.tiles_for_box((0, 0, 1000, 500), 1000, 500) == (1, 1)
|
||
|
||
|
||
def test_tiles_for_box_dense():
|
||
assert tl.tiles_for_box((0, 0, 2000, 1000), 1000, 500) == (2, 2)
|
||
|
||
|
||
def test_tiles_for_box_overlap_increases_count():
|
||
assert tl.tiles_for_box((0, 0, 1000, 500), 1000, 500, overlap=0.1) == (2, 2)
|
||
|
||
|
||
def test_tiles_for_box_invalid():
|
||
assert tl.tiles_for_box(None, 10, 10) == (1, 1)
|
||
assert tl.tiles_for_box((0, 0, 0, 0), 10, 10) == (1, 1)
|
||
assert tl.tiles_for_box((0, 0, 10, 10), 0, 10) == (1, 1)
|
||
|
||
|
||
def test_subdivide_row_major_top_first():
|
||
wins = tl.subdivide((0, 0, 100, 100), 2, 2)
|
||
assert len(wins) == 4
|
||
assert wins[0] == {"min_x": 0.0, "min_y": 50.0, "max_x": 50.0, "max_y": 100.0}
|
||
assert wins[1] == {"min_x": 50.0, "min_y": 50.0, "max_x": 100.0, "max_y": 100.0}
|
||
assert wins[2] == {"min_x": 0.0, "min_y": 0.0, "max_x": 50.0, "max_y": 50.0}
|
||
assert wins[3] == {"min_x": 50.0, "min_y": 0.0, "max_x": 100.0, "max_y": 50.0}
|
||
|
||
|
||
def test_subdivide_overlap_expands_then_clamps():
|
||
wins = tl.subdivide((0, 0, 100, 100), 2, 2, overlap=0.1, frame_win=(0, 0, 100, 100))
|
||
# 每格 50x50，外扩 5 → 左上格：x 0..55（左被夹到 0），y 45..100（上被夹到 100）
|
||
assert wins[0] == {"min_x": 0.0, "min_y": 45.0, "max_x": 55.0, "max_y": 100.0}
|
||
|
||
|
||
# --- plan_regions -----------------------------------------------------------
|
||
|
||
def test_plan_regions_sparse_single_tile():
|
||
frame = _frame((0, 0, 1000, 500))
|
||
clusters = [_cluster((100, 100, 400, 300))]
|
||
wins = tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50))
|
||
assert len(wins) == 1
|
||
assert wins[0]["min_x"] <= 100 and wins[0]["max_x"] >= 400
|
||
|
||
|
||
def test_plan_regions_dense_splits():
|
||
frame = _frame((0, 0, 2000, 1000))
|
||
clusters = [_cluster((0, 0, 2000, 1000))]
|
||
wins = tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50))
|
||
assert len(wins) == 4 # 2x2
|
||
|
||
|
||
def test_plan_regions_text_uses_finer_scale():
|
||
frame = _frame((0, 0, 1000, 500))
|
||
clusters = [_cluster((0, 0, 1000, 500))]
|
||
line_only = tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50))
|
||
text = tl.plan_regions(frame, clusters, text_clusters={0}, s_text=5.0,
|
||
s_line=10.0, view_px=(100, 50))
|
||
assert len(line_only) == 1
|
||
assert len(text) == 4 # 半径减半 → 2x2
|
||
|
||
|
||
def test_plan_regions_text_cluster_prioritized_on_truncation():
|
||
frame = _frame((0, 0, 4000, 2000))
|
||
clusters = [_cluster((0, 0, 2000, 1000), count=99), # 非文字，排前面（输入序）
|
||
_cluster((2000, 1000, 4000, 2000), count=1)] # 文字
|
||
wins = tl.plan_regions(frame, clusters, text_clusters={1},
|
||
s_text=10.0, s_line=10.0, view_px=(100, 50), max_tiles=2)
|
||
assert len(wins) == 2
|
||
# 文字簇（下标 1，位于右上）应优先出图
|
||
assert wins[0]["min_x"] >= 2000 and wins[0]["min_y"] >= 1000
|
||
|
||
|
||
def test_plan_regions_keep_filters_empty_tiles():
|
||
"""`keep` 谓词按占用情况剔除空瓦片（L 形分布时省下大片空白）。"""
|
||
frame = _frame((0, 0, 2000, 1000))
|
||
clusters = [_cluster((0, 0, 2000, 1000))]
|
||
assert len(tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50))) == 4
|
||
|
||
def keep_top(win):
|
||
return win["min_y"] >= 500 # 只保留上半（row 0）
|
||
|
||
wins = tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50),
|
||
keep=keep_top)
|
||
assert len(wins) == 2
|
||
assert all(w["min_y"] >= 500 for w in wins)
|
||
|
||
|
||
def test_plan_regions_degrades():
|
||
frame = _frame((0, 0, 1000, 500))
|
||
clusters = [_cluster((0, 0, 1000, 500))]
|
||
assert tl.plan_regions(frame, clusters, s_line=0.0, view_px=(100, 50)) == []
|
||
assert tl.plan_regions(frame, clusters, s_line=10.0, view_px=(0, 0)) == []
|
||
assert tl.plan_regions({"bbox": [0, 0, 0, 0]}, clusters, s_line=10.0,
|
||
view_px=(100, 50)) == []
|
||
assert tl.plan_regions(frame, [], s_line=10.0, view_px=(100, 50)) == []
|
||
|
||
|
||
def test_plan_regions_clamps_to_frame():
|
||
frame = _frame((0, 0, 1000, 500))
|
||
clusters = [_cluster((0, 0, 2000, 1000))] # 超出图框
|
||
wins = tl.plan_regions(frame, clusters, s_line=10.0, view_px=(100, 50), max_tiles=4)
|
||
for w in wins:
|
||
assert w["min_x"] >= 0 and w["max_x"] <= 1000
|
||
assert w["min_y"] >= 0 and w["max_y"] <= 500
|
||
|
||
|
||
# --- box / window 互转与可见范围 -------------------------------------------
|
||
|
||
def test_box_window_roundtrip():
|
||
box = (1.0, 2.0, 3.0, 4.0)
|
||
win = tl.box_to_window(box)
|
||
assert win == {"min_x": 1.0, "min_y": 2.0, "max_x": 3.0, "max_y": 4.0}
|
||
assert tl.window_to_box(win) == box
|
||
|
||
|
||
def test_box_to_window_invalid():
|
||
assert tl.box_to_window(None) is None
|
||
assert tl.box_to_window([1, 2, 3]) is None
|
||
|
||
|
||
def test_window_to_box_invalid():
|
||
assert tl.window_to_box(None) is None
|
||
assert tl.window_to_box({}) is None
|
||
assert tl.window_to_box({"min_x": 1, "min_y": 2}) is None
|
||
|
||
|
||
def test_expand_box_by_fraction():
|
||
assert tl.expand_box((0, 0, 100, 50), 0.05) == pytest.approx((-5.0, -2.5, 105.0, 52.5))
|
||
assert tl.expand_box((0, 0, 100, 50), 0.0) == (0.0, 0.0, 100.0, 50.0)
|
||
assert tl.expand_box(None, 0.1) is None
|
||
# 非法 frac 视为 0（不抛异常）
|
||
assert tl.expand_box((0, 0, 10, 10), "x") == (0.0, 0.0, 10.0, 10.0)
|
||
|
||
|
||
def test_visible_box_widens_to_viewport_aspect():
|
||
# 1000x500 的窗口在 1280x280（约 4.57:1）视口下等比适配 → 横向露出更多，纵向刚好贴合
|
||
vis = tl.visible_box((0, 0, 1000, 500), (1280, 280), 0.0)
|
||
assert vis[0] < 0 and vis[2] > 1000
|
||
assert vis[1] == pytest.approx(0.0)
|
||
assert vis[3] == pytest.approx(500.0)
|
||
assert (vis[0] + vis[2]) / 2 == pytest.approx(500.0) # 中心不变
|
||
assert (vis[1] + vis[3]) / 2 == pytest.approx(250.0)
|
||
|
||
|
||
def test_visible_box_tall_window_is_fit_by_height():
|
||
# 100x1000（很窄很高）在 1280x280 视口下按**高**适配 → 纵向刚好贴合，横向大幅露出
|
||
vis = tl.visible_box((0, 0, 100, 1000), (1280, 280), 0.0)
|
||
assert vis[1] == pytest.approx(0.0) and vis[3] == pytest.approx(1000.0)
|
||
assert vis[0] < 0 and vis[2] > 100
|
||
assert (vis[0] + vis[2]) / 2 == pytest.approx(50.0) # 中心不变
|
||
|
||
|
||
def test_visible_box_without_view_px_falls_back_to_margin():
|
||
assert tl.visible_box((0, 0, 100, 50), None, 0.1) == pytest.approx(
|
||
(-10.0, -5.0, 110.0, 55.0)
|
||
)
|
||
assert tl.visible_box((0, 0, 100, 50), (0, 0), 0.0) == (0.0, 0.0, 100.0, 50.0)
|
||
|
||
|
||
def test_visible_box_invalid_box():
|
||
assert tl.visible_box(None, (100, 100), 0.1) is None
|