feat: 拆分 DXF 解析为模块化结构，新增图层分析和实体分析模块

- 新增 layer_analysis.py：图层实体统计 + 角色推断（22条启发式规则） - 新增 entity_analysis.py：实体类型统计、INSERT 块聚合、文本提取 - 重构 main.py：调度分析模块，输出 {文件名}_cad_analysis.json - 新增 README.md 使用说明 - 输出文件名使用模型名作为前缀，避免多次测试覆盖
2026-07-08 14:31:27 +08:00
parent 6501364164
commit 9feeb14910
5 changed files with 428 additions and 394 deletions
@@ -0,0 +1,148 @@
+"""实体分析模块 —— 统计模型空间中各实体类型的数量、INSERT 块聚合、文本提取。"""
+
+
+def _extract_entity_props(entity):
+    """提取单个实体的关键属性为 JSON 友好格式。"""
+    dxftype = entity.dxftype()
+    props = {}
+
+    if dxftype == "LINE":
+        props["start"] = list(entity.dxf.start)
+        props["end"] = list(entity.dxf.end)
+    elif dxftype == "CIRCLE":
+        props["center"] = list(entity.dxf.center)
+        props["radius"] = round(entity.dxf.radius, 4)
+    elif dxftype == "ARC":
+        props["center"] = list(entity.dxf.center)
+        props["radius"] = round(entity.dxf.radius, 4)
+        props["start_angle"] = round(entity.dxf.start_angle, 1)
+        props["end_angle"] = round(entity.dxf.end_angle, 1)
+    elif dxftype == "LWPOLYLINE":
+        pts = entity.get_points()
+        props["vertex_count"] = len(entity)
+        props["closed"] = entity.closed
+        props["points"] = [[round(p[0], 4), round(p[1], 4)] for p in pts]
+    elif dxftype == "POLYLINE":
+        verts = list(entity.vertices())
+        props["vertex_count"] = len(verts)
+        props["points"] = [[round(v.dxf.location[0], 4), round(v.dxf.location[1], 4)] for v in verts]
+    elif dxftype == "INSERT":
+        props["block_name"] = entity.dxf.name
+        props["insert"] = list(entity.dxf.insert)
+        props["scale"] = [round(entity.dxf.xscale, 2), round(entity.dxf.yscale, 2), round(entity.dxf.zscale, 2)]
+        props["rotation"] = round(entity.dxf.rotation, 2)
+    elif dxftype in ("MTEXT", "TEXT"):
+        text = entity.plain_text() if dxftype == "MTEXT" else entity.dxf.text
+        props["text"] = text
+        if hasattr(entity.dxf, "insert"):
+            props["insert"] = list(entity.dxf.insert)
+        if hasattr(entity.dxf, "height"):
+            props["height"] = round(entity.dxf.height, 2)
+    elif dxftype == "DIMENSION":
+        props["text"] = entity.dxf.text
+        if hasattr(entity.dxf, "dimtype"):
+            props["dimtype"] = entity.dxf.dimtype
+    elif dxftype == "HATCH":
+        props["pattern"] = entity.dxf.pattern_name
+    elif dxftype in ("SOLID", "TRACE"):
+        for vi in range(4):
+            try:
+                v = getattr(entity.dxf, f"vtx{vi}")
+                props[f"vtx{vi}"] = list(v) if v else None
+            except Exception:
+                break
+    elif dxftype == "POINT":
+        props["location"] = list(entity.dxf.location)
+    elif dxftype == "ELLIPSE":
+        props["center"] = list(entity.dxf.center)
+        props["major_axis"] = list(entity.dxf.major_axis)
+        props["ratio"] = round(entity.dxf.ratio, 4)
+    elif dxftype == "SPLINE":
+        props["fit_points"] = [list(p) for p in entity.fit_points]
+    elif dxftype == "3DFACE":
+        for vi in range(4):
+            try:
+                v = getattr(entity.dxf, f"vtx{vi}")
+                props[f"vtx{vi}"] = list(v) if v else None
+            except Exception:
+                break
+    else:
+        for attr in entity.dxf.all_existing_dxf_attribs():
+            if attr in ("handle", "owner", "layer", "linetype", "color", "lineweight"):
+                continue
+            val = getattr(entity.dxf, attr)
+            if val is not None:
+                props[attr] = list(val) if hasattr(val, "__iter__") and not isinstance(val, str) else val
+
+    return props
+
+
+def analyze_entities(doc) -> dict:
+    """分析模型空间中的所有实体。
+
+    Args:
+        doc: ezdxf Drawing 对象
+
+    Returns:
+        dict: {
+            "total_entities": int,
+            "type_counts": dict,        # {dxftype: count}
+            "blocks": list[dict],        # INSERT 按块名聚合
+            "texts": list[dict],         # TEXT/MTEXT 文本列表
+        }
+    """
+    msp = doc.modelspace()
+    type_counts = {}
+
+    # INSERT 按块名聚合
+    block_map = {}  # block_name -> list of insert_info
+    texts = []
+
+    for entity in msp:
+        dxftype = entity.dxftype()
+        type_counts[dxftype] = type_counts.get(dxftype, 0) + 1
+
+        if dxftype == "INSERT":
+            block_name = entity.dxf.name
+            insert_info = {
+                "handle": entity.dxf.handle,
+                "layer": entity.dxf.layer,
+                "insert_point": list(entity.dxf.insert),
+                "rotation": round(entity.dxf.rotation, 2),
+                "scale": [
+                    round(entity.dxf.xscale, 2),
+                    round(entity.dxf.yscale, 2),
+                    round(entity.dxf.zscale, 2),
+                ],
+            }
+            if block_name not in block_map:
+                block_map[block_name] = []
+            block_map[block_name].append(insert_info)
+
+        elif dxftype in ("TEXT", "MTEXT"):
+            content = entity.plain_text() if dxftype == "MTEXT" else entity.dxf.text
+            text_info = {
+                "handle": entity.dxf.handle,
+                "layer": entity.dxf.layer,
+                "type": dxftype,
+                "content": content,
+            }
+            if hasattr(entity.dxf, "insert"):
+                text_info["insert"] = list(entity.dxf.insert)
+            texts.append(text_info)
+
+    # 块聚合结果
+    blocks = []
+    for block_name, inserts in sorted(block_map.items()):
+        blocks.append({
+            "block_name": block_name,
+            "count": len(inserts),
+            "inserts": inserts,
+        })
+
+    return {
+        "total_entities": sum(type_counts.values()),
+        "type_counts": type_counts,
+        "blocks": blocks,
+        "texts": texts,
+    }