drawing-analyzer

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
name: "drawing-analyzer"
description: "Analyze construction drawings to extract dimensions, annotations, symbols, and metadata. Support quantity takeoff and design review automation."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "📑", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# Drawing Analyzer for Construction

## Overview

Analyze construction drawings (PDF, DWG) to extract dimensions, annotations, symbols, title block data, and support automated quantity takeoff and design review.

## Business Case

Drawing analysis automation enables:
- **Faster Takeoffs**: Extract quantities from drawings
- **Quality Control**: Verify drawing completeness
- **Data Extraction**: Pull metadata for project systems
- **Design Review**: Automated checking against standards

## Technical Implementation

```python
from dataclasses import dataclass, field
from typing import List, Dict, Any, Optional, Tuple
import re
import pdfplumber
from pathlib import Path

@dataclass
class TitleBlockData:
    project_name: str
    project_number: str
    sheet_number: str
    sheet_title: str
    discipline: str
    scale: str
    date: str
    revision: str
    drawn_by: str
    checked_by: str
    approved_by: str

@dataclass
class Dimension:
    value: float
    unit: str
    dimension_type: str  # linear, angular, radial
    location: Tuple[float, float]
    associated_text: str

@dataclass
class Annotation:
    text: str
    annotation_type: str  # note, callout, tag, keynote
    location: Tuple[float, float]
    references: List[str]

@dataclass
class Symbol:
    symbol_type: str  # door, window, equipment, etc.
    tag: str
    location: Tuple[float, float]
    properties: Dict[str, Any]

@dataclass
class DrawingAnalysisResult:
    file_name: str
    title_block: Optional[TitleBlockData]
    dimensions: List[Dimension]
    annotations: List[Annotation]
    symbols: List[Symbol]
    scale_factor: float
    drawing_area: Tuple[float, float]
    quality_issues: List[str]

class DrawingAnalyzer:
    """Analyze construction drawings for data extraction."""

    # Common dimension patterns
    DIMENSION_PATTERNS = [
        r"(\d+'-\s*\d+(?:\s*\d+/\d+)?\"?)",  # Feet-inches: 10'-6", 10' - 6 1/2"
        r"(\d+(?:\.\d+)?)\s*(?:mm|cm|m|ft|in)",  # Metric/imperial with unit
        r"(\d+'-\d+\")",  # Compact feet-inches
        r"(\d+)\s*(?:SF|LF|CY|EA)",  # Quantity dimensions
    ]

    # Common annotation patterns
    ANNOTATION_PATTERNS = {
        'keynote': r'^\d{1,2}[A-Z]?$',  # 1A, 12, 5B
        'room_tag': r'^(?:RM|ROOM)\s*\d+',
        'door_tag': r'^[A-Z]?\d{2,3}[A-Z]?$',
        'grid_line': r'^[A-Z]$|^\d+$',
        'elevation': r'^(?:EL|ELEV)\.?\s*\d+',
        'detail_ref': r'^\d+/[A-Z]\d+',
    }

    # Scale patterns
    SCALE_PATTERNS = [
        r"SCALE:\s*(\d+(?:/\d+)?)\s*[\"']\s*=\s*(\d+)\s*['\-]",  # 1/4" = 1'-0"
        r"(\d+):(\d+)",  # 1:100
        r"NTS|NOT TO SCALE",
    ]

    def __init__(self):
        self.results: Dict[str, DrawingAnalysisResult] = {}

    def analyze_pdf_drawing(self, pdf_path: str) -> DrawingAnalysisResult:
        """Analyze a PDF drawing."""
        path = Path(pdf_path)

        all_text = ""
        dimensions = []
        annotations = []
        symbols = []
        quality_issues = []

        with pdfplumber.open(pdf_path) as pdf:
            for page in pdf.pages:
                # Extract text
                text = page.extract_text() or ""
                all_text += text + "\n"

                # Extract dimensions
                page_dims = self._extract_dimensions(text)
                dimensions.extend(page_dims)

                # Extract annotations
                page_annots = self._extract_annotations(text)
                annotations.extend(page_annots)

                # Extract from tables (often contain schedules)
                tables = page.extract_tables()