fix: detect Revit floor frames deterministically

This commit is contained in:
2026-07-21 11:03:38 +08:00
parent a6856f903d
commit 87afe63313
4 changed files with 494 additions and 38 deletions

View File

@@ -11,7 +11,7 @@ import os
import shutil
import subprocess
import sys
from collections import Counter
from collections import Counter, defaultdict
from pathlib import Path
@@ -244,6 +244,16 @@ import re as _re
PLAN_TITLE_RE = _re.compile(r"平面图$")
PLAN_TITLE_EXCLUDE_RE = _re.compile(r"(示意|疏散|分区|索引|定位|总平面|放大|详图|布置|大样)")
PLAN_TITLE_EXCLUDE_LAYERS = ("*图签*", "*PUB_TAB*", "*TTLB*", "*TK*", "*图框*", "*目录*")
CAD_TEXT_FORMAT_RE = _re.compile(r"\\[LlOoKk]|%%[UuOoKk]")
FLOOR_TOKEN_RE = _re.compile(
r"机房小屋面|机房屋面|"
r"地下[一二三四五六七八九十\d]+层夹层|"
r"地下[一二三四五六七八九十\d]+层|"
r"[一二三四五六七八九十\d]+层夹层|"
r"[一二三四五六七八九十\d]+层|"
r"首层|底层|夹层|屋顶层|屋顶|屋面|机房层|电梯机房"
)
# AutoCAD MIF escapes (\M+5XXXX): CJK text in pre-Unicode DWGs survives
# DXF conversion as literal escape sequences, so title matching must decode
@@ -267,27 +277,78 @@ def decode_mif(text: str) -> str:
return MIF_RE.sub(repl, text)
def normalize_cad_text(text: str) -> str:
text = CAD_TEXT_FORMAT_RE.sub("", decode_mif(text))
return text.replace("\\P", " ").strip()
def floor_identities(label: str) -> list[tuple[str, str]]:
"""``(building qualifier, floor)`` identities from labels/INSERT names."""
label = normalize_cad_text(label).replace("_", "、")
if label.endswith(("机房小屋面", "机房屋面")):
return [("", "PH")]
if not label.endswith("平面图") or len(label) > 50:
return []
head = label[:-3]
matches = list(FLOOR_TOKEN_RE.finditer(head))
tokens = [match.group(0) for match in matches]
qualifier = _re.sub(r"[、,,\s]+$", "", head[:matches[0].start()]) if matches else ""
if len(qualifier) > 12:
qualifier = ""
out = []
for token in tokens:
if token in {"屋顶层", "屋顶", "屋面"}:
out.append("RF")
elif token in {"机房小屋面", "机房屋面", "机房层", "电梯机房"}:
out.append("PH")
elif token == "首层":
out.append("F1")
elif token == "底层":
out.append("B1")
elif token == "夹层":
out.append("F1M")
else:
out.append(token)
return [(qualifier, identity) for identity in out] or [("", label)]
def count_plan_titles(entities) -> int:
"""Distinct plan-frame titles in modelspace (multi-frame sheet detector)."""
seen = set()
"""Distinct plan floors from visible titles and Revit INSERT-name suffixes."""
floor_qualifiers: dict[str, set[str]] = defaultdict(set)
for entity in entities:
kind = entity.dxftype()
if kind == "INSERT":
try:
suffix = str(entity.dxf.name).rsplit("-", 1)[-1]
except Exception:
continue
for qualifier, floor in floor_identities(suffix):
floor_qualifiers[floor].add(qualifier)
continue
if kind not in {"TEXT", "MTEXT"}:
continue
try:
layer = str(entity.dxf.layer)
except Exception:
layer = ""
if any(fnmatch.fnmatch(layer.upper(), pattern.upper()) for pattern in PLAN_TITLE_EXCLUDE_LAYERS):
continue
try:
text = str(entity.dxf.text if kind == "TEXT" else entity.plain_text() or "").strip()
except Exception:
continue
text = decode_mif(text)
text = normalize_cad_text(text)
if not text or len(text) > 40:
continue
if PLAN_TITLE_RE.search(text) and not PLAN_TITLE_EXCLUDE_RE.search(text):
try:
pos = entity.dxf.insert
seen.add((text, round(float(pos.x) / 5000), round(float(pos.y) / 5000)))
except Exception:
seen.add((text, 0, 0))
return len(seen)
for qualifier, floor in floor_identities(text):
floor_qualifiers[floor].add(qualifier)
# Revit repeats the same floor suffix across hundreds of family INSERTs;
# a sheet-title block may add ``主楼`` while families remain unqualified.
# Count that as one frame, but retain two genuinely different qualified
# buildings that both contain (say) an F1 plan in the same modelspace.
return sum(max(1, len({q for q in qualifiers if q}))
for qualifiers in floor_qualifiers.values())
def insert_block_content(doc, entities) -> list[dict]: