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

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()
                for table in tables:
                    symbols.extend(self._parse_schedule_table(table))

        # Parse title block
        title_block = self._extract_title_block(all_text)

        # Determine scale
        scale_factor = self._determine_scale(all_text)

        # Quality checks
        quality_issues = self._check_drawing_quality(
            title_block, dimensions, annotations
        )

        result = DrawingAnalysisResult(
            file_name=path.name,
            title_block=title_block,
            dimensions=dimensions,
            annotations=annotations,
            symbols=symbols,
            scale_factor=scale_factor,
            drawing_area=(0, 0),  # Would need image analysis
            quality_issues=quality_issues
        )

        self.results[path.name] = result
        return result

    def _extract_dimensions(self, text: str) -> List[Dimension]:
        """Extract dimensions from text."""
        dimensions = []

        for pattern in self.DIMENSION_PATTERNS:
            matches = re.findall(pattern, text)
            for match in matches:
                value, unit = self._parse_dimension_value(match)
                if value > 0:
                    dimensions.append(Dimension(
                        value=value,
                        unit=unit,
                        dimension_type='linear',
                        location=(0, 0),
                        associated_text=match
                    ))

        return dimensions

    def _parse_dimension_value(self, dim_text: str) -> Tuple[float, str]:
        """Parse dimension text to value and unit."""
        dim_text = dim_text.strip()

        # Feet and inches: 10'-6"
        ft_in_match = re.match(r"(\d+)'[-\s]*(\d+)?(?:\s*(\d+)/(\d+))?\"?", dim_text)
        if ft_in_match:
            feet = int(ft_in_match.group(1))
            inches = int(ft_in_match.group(2) or 0)
            if ft_in_match.group(3) and ft_in_match.group(4):
                inches += int(ft_in_match.group(3)) / int(ft_in_match.group(4))
            return feet * 12 + inches, 'in'

        # Metric with unit
        metric_match = re.match(r"(\d+(?:\.\d+)?)\s*(mm|cm|m)", dim_text)
        if metric_match:
            return float(metric_match.group(1)), metric_match.group(2)

        # Just a number
        num_match = re.match(r"(\d+(?:\.\d+)?)", dim_text)
        if num_match:
            return float(num_match.group(1)), ''

        return 0, ''

    def _extract_annotations(self, text: str) -> List[Annotation]:
        """Extract annotations from text."""
        annotations = []
        lines = text.split('\n')

        for line in lines:
            line = line.strip()
            if not line:
                continue

            for annot_type, pattern in self.ANNOTATION_PATTERNS.items():
                if re.match(pattern, line, re.IGNORECASE):
                    annotations.append(Annotation(
                        text=line,
                        annotation_type=annot_type,
                        location=(0, 0),
                        references=[]
                    ))
                    break

            # General notes
            if line.startswith(('NOTE:', 'SEE ', 'REFER TO', 'TYP', 'U.N.O.')):
                annotations.append(Annotation(
                    text=line,
                    annotation_type='note',
                    location=(0, 0),
                    references=[]
                ))

        return annotations

    def _extract_title_block(self, text: str) -> Optional[TitleBlockData]:
        """Extract title block information."""
        # Common title block patterns
        patterns = {
            'project_name': r'PROJECT(?:\s*NAME)?:\s*(.+?)(?:\n|$)',
            'project_number': r'(?:PROJECT\s*)?(?:NO|NUMBER|#)\.?:\s*(\S+)',
            'sheet_number': r'SHEET(?:\s*NO)?\.?:\s*([A-Z]?\d+(?:\.\d+)?)',
            'sheet_title': r'SHEET\s*TITLE:\s*(.+?)(?:\n|$)',
            'scale': r'SCALE:\s*(.+?)(?:\n|$)',
            'date': r'DATE:\s*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})',
            'revision': r'REV(?:ISION)?\.?:\s*(\S+)',
            'drawn_by': r'(?:DRAWN|DRN)\s*(?:BY)?:\s*(\S+)',
            'checked_by': r'(?:CHECKED|CHK)\s*(?:BY)?:\s*(\S+)',
        }

        extracted = {}
        for field, pattern in patterns.items():
            match = re.search(pattern, text, re.IGNOR